© 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. 31078
    Prev
    Next
    INDEX
    Explanations

    phrases related to permissions and consent

    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
    isel
    -0.08
    sik
    -0.07
    outes
    -0.07
    rente
    -0.07
    uiltin
    -0.06
    chure
    -0.06
    agas
    -0.06
    aos
    -0.06
    arden
    -0.06
    /Dk
    -0.06
    POSITIVE LOGITS
     aid
    0.06
     tide
    0.06
     âĹĦ
    0.06
    itos
    0.06
    ugi
    0.06
    ighton
    0.06
    &S
    0.06
     Singleton
    0.06
    اط
    0.06
     jeg
    0.06
    Activations Density 0.003%

    No Known Activations