© 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. 54099
    Prev
    Next
    INDEX
    Explanations

    references to time-related events or seasons

    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
    ukes
    -0.06
     SpoleÄį
    -0.06
    ़ि
    -0.06
    vine
    -0.06
    anken
    -0.06
    YLON
    -0.06
    imb
    -0.06
    _AUD
    -0.06
    bias
    -0.06
    tps
    -0.06
    POSITIVE LOGITS
     eldre
    0.06
    esti
    0.06
     ÛĮعÙĨÛĮ
    0.06
     Hancock
    0.06
    pole
    0.06
    adt
    0.06
    igli
    0.06
    ī
    0.06
     Ùħباش
    0.06
    ooke
    0.06
    Activations Density 0.031%

    No Known Activations