© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 20-LLAMASCOPE-RES-32K
    11. 16280
    Prev
    Next
    INDEX
    Explanations

    words or phrases that introduce contrasting or qualifying statements, particularly "however" and similar transitional words.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @maxsloeffler

    discussions related to societal issues and the impact of actions on communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Yol
    -0.15
    ox
    -0.15
    iku
    -0.15
     Garner
    -0.15
    ABCDEFGHI
    -0.15
     HomeComponent
    -0.14
    zan
    -0.14
     impress
    -0.14
    ίκ
    -0.14
    ERG
    -0.14
    POSITIVE LOGITS
     usage
    0.20
    mund
    0.18
     everyone
    0.17
    umbed
    0.17
    Usage
    0.17
     Usage
    0.17
    ected
    0.16
    usage
    0.15
     everybody
    0.15
    everyone
    0.15
    Activations Density 0.007%

    No Known Activations