© 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. 9-LLAMASCOPE-RES-131K
    11. 94956
    Prev
    Next
    INDEX
    Explanations

    expressions of knowledge or awareness of commonly accepted truths

    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
     coloring
    -0.07
    ymoon
    -0.07
    iggins
    -0.06
    mez
    -0.06
    ounge
    -0.06
    ovie
    -0.06
     bay
    -0.06
     ((
    -0.06
    iman
    -0.06
    onda
    -0.06
    POSITIVE LOGITS
    oti
    0.08
    clid
    0.07
     intervening
    0.06
    èĸ
    0.06
    оÑĤи
    0.06
    OT
    0.06
    oten
    0.06
    uchar
    0.06
    LTE
    0.06
     Muk
    0.06
    Activations Density 0.005%

    No Known Activations