© 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. 40261
    Prev
    Next
    INDEX
    Explanations

    numerical values related to historical events or significant time periods

    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
    olean
    -0.06
    orks
    -0.06
    ocre
    -0.06
    ayd
    -0.06
    pard
    -0.06
    velt
    -0.06
     åħĥ
    -0.06
     Kraj
    -0.06
    ustomed
    -0.06
    ätz
    -0.06
    POSITIVE LOGITS
    /or
    0.09
     alike
    0.09
    /WebAPI
    0.08
    AMP
    0.07
    raquo
    0.07
     filetype
    0.07
    oulder
    0.07
     hatta
    0.07
     amp
    0.07
    amp
    0.07
    Activations Density 0.003%

    No Known Activations