© 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. 1174
    Prev
    Next
    INDEX
    Explanations

    references to personal growth and transformation

    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
    -fontawesome
    -0.07
    láš
    -0.07
    ÃŃÅ¡
    -0.07
    entin
    -0.07
    има
    -0.06
    опиÑģ
    -0.06
    isper
    -0.06
     +=↵
    -0.06
    innen
    -0.06
    oui
    -0.06
    POSITIVE LOGITS
     himself
    0.27
     themselves
    0.22
     herself
    0.22
     myself
    0.20
     Himself
    0.19
    èĩªå·±
    0.18
     itself
    0.18
     yourself
    0.18
     oneself
    0.17
     ourselves
    0.17
    Activations Density 0.044%

    No Known Activations