© 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. 55851
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and reflections on perceptions of culture

    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
     باب
    -0.07
    ëĭ´
    -0.06
    ilip
    -0.06
    PEG
    -0.06
    ounder
    -0.06
    oop
    -0.06
    ÑİÑĢ
    -0.06
     Babies
    -0.06
    lex
    -0.06
     Sez
    -0.06
    POSITIVE LOGITS
     institution
    0.07
    gre
    0.07
    iesz
    0.06
     Institution
    0.06
    ocs
    0.06
    æĬľ
    0.06
     Went
    0.06
    rove
    0.06
    acebook
    0.06
    ereotype
    0.06
    Activations Density 0.006%

    No Known Activations