© 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. 17-LLAMASCOPE-RES-131K
    11. 107660
    Prev
    Next
    INDEX
    Explanations

    actions and activities depicted in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    b
    -0.10
    r
    -0.09
    p
    -0.09
    c
    -0.09
    w
    -0.08
    d
    -0.08
    x
    -0.08
    in
    -0.08
    h
    -0.08
     latter
    -0.07
    POSITIVE LOGITS
    ï¸ı
    0.12
    esus
    0.09
    ontent
    0.07
    ;element
    0.07
    аÐ
    0.07
    ulaire
    0.07
    rlen
    0.07
    ugins
    0.07
    een
    0.07
    endl
    0.07
    Activations Density 0.021%

    No Known Activations