© 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. 128748
    Prev
    Next
    INDEX
    Explanations

    expressions of personal goals and learning outcomes

    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
    akov
    -0.08
    930
    -0.07
    udden
    -0.07
    (éĩij
    -0.07
    icken
    -0.07
    ombs
    -0.07
    sÃŃ
    -0.07
    tember
    -0.07
    uellen
    -0.07
    æĭ¥æľī
    -0.07
    POSITIVE LOGITS
     gained
    0.09
     outcome
    0.08
     learn
    0.08
     gain
    0.08
     learns
    0.07
     gains
    0.07
     ìĸ»
    0.07
     During
    0.07
     outcomes
    0.07
     during
    0.07
    Activations Density 0.146%

    No Known Activations