© 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. 126002
    Prev
    Next
    INDEX
    Explanations

    names and references to well-known personalities or characters

    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
     addCriterion
    -0.09
    raž
    -0.08
    rowsable
    -0.07
    Forge
    -0.07
    itage
    -0.07
    omers
    -0.07
    Ģ
    -0.07
    ayette
    -0.07
    iglia
    -0.06
    liž
    -0.06
    POSITIVE LOGITS
    ypo
    0.08
    487
    0.07
    007
    0.07
     Tight
    0.07
    æ¸
    0.07
    426
    0.06
    erton
    0.06
    borg
    0.06
    owski
    0.06
     himself
    0.06
    Activations Density 0.084%

    No Known Activations