© 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. 117425
    Prev
    Next
    INDEX
    Explanations

    references to permissions, access, and legal agreements

    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
    yh
    -0.06
    eref
    -0.06
     meas
    -0.06
    _DECLARE
    -0.06
    NSE
    -0.06
    wer
    -0.06
    OOK
    -0.06
    ción
    -0.06
    jeta
    -0.06
    kos
    -0.06
    POSITIVE LOGITS
     certain
    0.07
    .ManyToMany
    0.07
     Certain
    0.07
    Certain
    0.07
    witter
    0.07
    acomment
    0.06
    .setInput
    0.06
    ald
    0.06
    à¥Įà¤ķ
    0.06
    peg
    0.06
    Activations Density 0.003%

    No Known Activations