© 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. 119081
    Prev
    Next
    INDEX
    Explanations

    statistical data related to populations and market demographics

    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
    iminal
    -0.07
    ç½²
    -0.06
    itech
    -0.06
    .opend
    -0.06
     maximal
    -0.06
    öst
    -0.06
    resh
    -0.06
    á»ĩ
    -0.06
    ogo
    -0.06
    736
    -0.06
    POSITIVE LOGITS
    вÑĸ
    0.07
     brands
    0.07
     Brands
    0.07
     households
    0.07
     Arbit
    0.07
     Nielsen
    0.06
     brand
    0.06
     audiences
    0.06
    طاÙĦ
    0.06
    CRET
    0.06
    Activations Density 0.004%

    No Known Activations