© 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. 129141
    Prev
    Next
    INDEX
    Explanations

    references to cultural concepts and their implications

    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
    TypeEnum
    -0.07
    asal
    -0.07
    /browse
    -0.06
    erra
    -0.06
    iant
    -0.06
    deg
    -0.06
    bose
    -0.06
    /authentication
    -0.06
    367
    -0.06
    /callback
    -0.06
    POSITIVE LOGITS
    -wide
    0.09
    wide
    0.07
     wide
    0.07
    .Toolkit
    0.07
    /Framework
    0.06
     cond
    0.06
     context
    0.06
    /context
    0.06
     ÑĪп
    0.06
    -Americ
    0.06
    Activations Density 0.012%

    No Known Activations