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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 7-LLAMASCOPE-RES-32K
    11. 14326
    Prev
    Next
    INDEX
    Explanations

    explicit language and profanity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tex
    -0.15
    borg
    -0.14
    ussen
    -0.14
     Mam
    -0.14
    atas
    -0.14
     иÑģÑĤ
    -0.14
    kip
    -0.14
    æĬĺ
    -0.14
    vil
    -0.14
    idel
    -0.13
    POSITIVE LOGITS
    esper
    0.15
     numberOfRows
    0.15
    δÏģα
    0.15
    á»į
    0.15
    elper
    0.14
    εÏī
    0.14
     Colleg
    0.14
    IFO
    0.13
    INDOW
    0.13
    ITICAL
    0.13
    Activations Density 0.017%

    No Known Activations