© 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. 28854
    Prev
    Next
    INDEX
    Explanations

    expressions of self-doubt and the struggles of an artist

    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
    dock
    -0.07
    uw
    -0.06
    asi
    -0.06
    ynet
    -0.06
    u
    -0.06
    onden
    -0.06
     Media
    -0.05
     associate
    -0.05
    urch
    -0.05
     Audio
    -0.05
    POSITIVE LOGITS
    TEGER
    0.07
    ÅĻez
    0.07
    Ñĵ
    0.07
    _deep
    0.07
    .sul
    0.07
    HOOK
    0.07
    Ä°S
    0.07
    453
    0.07
    ungan
    0.07
     Writer
    0.07
    Activations Density 0.002%

    No Known Activations