© 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. 76338
    Prev
    Next
    INDEX
    Explanations

    commands or functions related to searching and file handling

    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
    uds
    -0.07
    endforeach
    -0.07
    æľĭ
    -0.07
    raising
    -0.07
     *__
    -0.07
    coop
    -0.07
    ãĥ¼ãĥĸãĥ«
    -0.07
     Rol
    -0.07
    /reset
    -0.06
    alach
    -0.06
    POSITIVE LOGITS
     awk
    0.07
    279
    0.06
     exig
    0.06
     mailed
    0.06
     Loren
    0.06
    ìĹŃ
    0.06
    ABS
    0.06
     sed
    0.06
    .Lines
    0.06
    dad
    0.06
    Activations Density 0.001%

    No Known Activations