© 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. 17-LLAMASCOPE-RES-131K
    11. 60698
    Prev
    Next
    INDEX
    Explanations

    references to Supreme Court justices' names or associated terms

    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
    igid
    -0.06
    ùa
    -0.06
     Wich
    -0.06
    afia
    -0.06
    itou
    -0.06
    ignon
    -0.06
    ãģ¼
    -0.06
     ç¸
    -0.06
    ibri
    -0.06
    ιν
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.06
     SUBSTITUTE
    0.06
     substitute
    0.06
     Yes
    0.06
     Depends
    0.06
    ë¡Ģ
    0.06
     Substitute
    0.06
     NA
    0.06
    enza
    0.06
     Chic
    0.06
    Activations Density 0.000%

    No Known Activations