© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 27222
    Prev
    Next
    INDEX
    Explanations

    phrases reflecting discussions of social identity and related concepts

    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
    .xlsx
    -0.06
    tuk
    -0.06
     os
    -0.06
    .scalablytyped
    -0.06
    ingle
    -0.05
    zbek
    -0.05
    conde
    -0.05
     mouth
    -0.05
    oric
    -0.05
     distribute
    -0.05
    POSITIVE LOGITS
    401
    0.07
    ivia
    0.07
    ÑıÑĩ
    0.06
    hdr
    0.06
    åī²
    0.06
     Duch
    0.06
    ãĥ¬ãĥ¼
    0.06
    Traits
    0.06
    ois
    0.06
    untime
    0.06
    Activations Density 0.048%

    No Known Activations