© 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. 91957
    Prev
    Next
    INDEX
    Explanations

    terms related to foul play or misconduct

    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
    elli
    -0.09
     Cru
    -0.09
    ext
    -0.08
    lite
    -0.07
    chaft
    -0.07
    s
    -0.06
    774
    -0.06
    ãģķãģĦ
    -0.06
    ellen
    -0.06
    i
    -0.06
    POSITIVE LOGITS
    -mouth
    0.08
    mouth
    0.08
    spo
    0.08
    ishment
    0.08
    weather
    0.07
    ution
    0.07
    .Ptr
    0.07
    Ľå»º
    0.07
    PIP
    0.07
    ernet
    0.07
    Activations Density 0.002%

    No Known Activations