© 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. 76945
    Prev
    Next
    INDEX
    Explanations

    instances of the keyword "AS."

    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
    ÅĻeh
    -0.07
    üç
    -0.07
    ston
    -0.07
    sten
    -0.07
    _guard
    -0.07
    addon
    -0.07
    ToFit
    -0.06
    vala
    -0.06
    antry
    -0.06
    isches
    -0.06
    POSITIVE LOGITS
    ghan
    0.07
    SEMB
    0.07
    semblies
    0.07
    sembl
    0.07
    riel
    0.07
    ameda
    0.07
    oti
    0.06
     respectively
    0.06
    eger
    0.06
    sembles
    0.06
    Activations Density 0.003%

    No Known Activations