© 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. 95173
    Prev
    Next
    INDEX
    Explanations

    expressions indicating disbelief or surprise

    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
    dig
    -0.06
    iesz
    -0.06
    quot
    -0.06
    oux
    -0.06
    iginal
    -0.06
    å´İ
    -0.06
    ÑĢиг
    -0.06
    Actions
    -0.06
    á»ĭch
    -0.06
    .resp
    -0.06
    POSITIVE LOGITS
    ingly
    0.07
    ible
    0.07
     sometimes
    0.06
    ì´
    0.06
     oneself
    0.06
    enance
    0.06
     Pol
    0.06
    erb
    0.06
    /not
    0.06
    _exempt
    0.06
    Activations Density 0.008%

    No Known Activations