© 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. 93593
    Prev
    Next
    INDEX
    Explanations

    expressions of sorrow or regret

    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
     ::::::::
    -0.08
    heimer
    -0.07
    andest
    -0.07
    âī¡
    -0.07
    utex
    -0.07
    eum
    -0.07
    agma
    -0.07
    NESS
    -0.06
    ArrayOf
    -0.06
    ubat
    -0.06
    POSITIVE LOGITS
    ably
    0.11
    ingly
    0.07
     lack
    0.07
    871
    0.07
    ation
    0.07
    aby
    0.06
    fully
    0.06
     Baz
    0.06
    ible
    0.06
    LOCKS
    0.06
    Activations Density 0.008%

    No Known Activations