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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 75276
    Prev
    Next
    INDEX
    Explanations

    certain file formats and programming-related tokens

    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
    reso
    -0.08
    utin
    -0.07
    razier
    -0.06
    лÑİб
    -0.06
    chester
    -0.06
    accent
    -0.06
    _repr
    -0.06
    ps
    -0.06
    nÄĽnÃŃ
    -0.06
    arin
    -0.06
    POSITIVE LOGITS
    ãĤ¤ãĥ«
    0.08
    ãĥ¼ãĥĨ
    0.07
     committed
    0.07
    دÙĩ
    0.07
     master
    0.07
    /master
    0.07
     vyž
    0.06
    äter
    0.06
     há»ĵi
    0.06
    ëĿ¼ìĿ¸
    0.06
    Activations Density 0.001%

    No Known Activations