© 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. 26385
    Prev
    Next
    INDEX
    Explanations

    numerical values or references to statistics and quantities

    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
     favors
    -0.19
     honor
    -0.18
     honorable
    -0.17
     honors
    -0.17
     molding
    -0.17
     Harbor
    -0.17
    avior
    -0.16
     honoring
    -0.16
     theater
    -0.16
     colorful
    -0.16
    POSITIVE LOGITS
    sdale
    0.15
    é£
    0.15
    à¸¸à¸Ľ
    0.14
    éĥ
    0.14
    croft
    0.14
     |_|
    0.14
     headline
    0.14
    ben
    0.14
    HEMA
    0.14
    .exc
    0.14
    Activations Density 0.125%

    No Known Activations