© 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. 61131
    Prev
    Next
    INDEX
    Explanations

    references to websites and sources

    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
    аÑĢан
    -0.07
    ulla
    -0.07
    æı´
    -0.07
    ãĥ³ãĤ¸
    -0.07
    Ñģли
    -0.07
    हम
    -0.07
    atten
    -0.06
    /problem
    -0.06
    лек
    -0.06
    isman
    -0.06
    POSITIVE LOGITS
    uto
    0.06
     hab
    0.06
    atak
    0.06
    290
    0.06
    icie
    0.06
    clair
    0.06
    _js
    0.05
    elta
    0.05
    ije
    0.05
    360
    0.05
    Activations Density 0.002%

    No Known Activations