© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3891
    Prev
    Next
    INDEX
    Explanations

    references to obligations, regulations, or procedural requirements

    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
    ABL
    -0.08
    лÑıд
    -0.07
    buie
    -0.07
    ãĥ¼ãĥĪ
    -0.07
    SSERT
    -0.07
    mar
    -0.07
    linger
    -0.07
    .Xaml
    -0.07
    argar
    -0.06
    unce
    -0.06
    POSITIVE LOGITS
     himself
    0.08
     herself
    0.07
    (es
    0.07
    cko
    0.07
    atsby
    0.07
     TextAlign
    0.06
    ariat
    0.06
    ActionCreators
    0.06
     myself
    0.06
     shades
    0.06
    Activations Density 0.034%

    No Known Activations