© 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. 80372
    Prev
    Next
    INDEX
    Explanations

    expressions of enthusiasm or admiration

    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
    sons
    -0.07
    ric
    -0.07
    ucci
    -0.07
    zw
    -0.07
    room
    -0.07
    rica
    -0.06
    tered
    -0.06
     Madness
    -0.06
    side
    -0.06
    inel
    -0.06
    POSITIVE LOGITS
    lest
    0.10
    byn
    0.07
    illance
    0.07
    gth
    0.07
    ç´ł
    0.07
    lection
    0.07
    assin
    0.07
    heat
    0.07
    egg
    0.07
    jÃŃm
    0.07
    Activations Density 0.006%

    No Known Activations