© 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. 105951
    Prev
    Next
    INDEX
    Explanations

    descriptive language that expresses personal impressions and artistic 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
    olet
    -0.07
     clients
    -0.07
     client
    -0.06
    perator
    -0.06
     Mil
    -0.06
     recent
    -0.06
     ourselves
    -0.06
     ours
    -0.06
     our
    -0.06
     last
    -0.06
    POSITIVE LOGITS
     tehdy
    0.08
    utas
    0.07
    иной
    0.07
    /proto
    0.07
    _guard
    0.06
    ħ
    0.06
    Equivalent
    0.06
    ÃŃÅĻ
    0.06
    ÅĻÃŃz
    0.06
    eyle
    0.06
    Activations Density 0.026%

    No Known Activations