© 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. 40102
    Prev
    Next
    INDEX
    Explanations

    the presence of personal pronouns and statements reflecting personal experiences or feelings

    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
     Absolutely
    -0.07
    oš
    -0.07
    obra
    -0.07
     абÑģолÑİÑĤно
    -0.06
    alone
    -0.06
     klu
    -0.06
    Absolutely
    -0.06
     therefore
    -0.06
    oÄŁlu
    -0.06
    hil
    -0.06
    POSITIVE LOGITS
     mainly
    0.09
     maybe
    0.08
    æ¯ķ
    0.08
     certainly
    0.08
     mostly
    0.07
    maybe
    0.07
     perhaps
    0.07
    ç±
    0.07
    553
    0.06
     Certainly
    0.06
    Activations Density 0.053%

    No Known Activations