© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 76124
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and semicolons

    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
    anke
    -0.07
    ouns
    -0.07
    gles
    -0.07
    ylon
    -0.07
    utut
    -0.07
    oun
    -0.07
    ward
    -0.07
    ROL
    -0.06
    piel
    -0.06
    odzi
    -0.06
    POSITIVE LOGITS
    lund
    0.07
    ?><
    0.06
    atisfaction
    0.06
    :animated
    0.06
    ì§Ī
    0.06
    ữu
    0.06
    tz
    0.05
    MT
    0.05
    bill
    0.05
    CRT
    0.05
    Activations Density 0.003%

    No Known Activations