© 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. 78133
    Prev
    Next
    INDEX
    Explanations

    references to individuals or personal experiences

    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
    uien
    -0.08
    rone
    -0.08
    wins
    -0.08
    raya
    -0.08
    icens
    -0.08
    ãģıãĤĵ
    -0.08
    ìĿ¸ìĿ´
    -0.08
    AFX
    -0.07
    mente
    -0.07
    abbo
    -0.07
    POSITIVE LOGITS
    oping
    0.13
     are
    0.10
    soever
    0.10
    oped
    0.08
    ever
    0.08
     has
    0.08
    upon
    0.08
    've
    0.08
     is
    0.07
     can
    0.07
    Activations Density 0.113%

    No Known Activations