© 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. 106471
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases that evoke evaluations or assessments

    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
    afen
    -0.07
    æ¦ľ
    -0.07
    )(*
    -0.07
     Dün
    -0.06
    apas
    -0.06
    usz
    -0.06
     liá»ģn
    -0.06
    رز
    -0.06
    .son
    -0.06
    δά
    -0.06
    POSITIVE LOGITS
     «
    0.10
     "
    0.09
     “
    0.07
     '
    0.07
     `
    0.07
    ardon
    0.07
     "(
    0.07
     "[
    0.07
     “[
    0.06
     """
    0.06
    Activations Density 0.025%

    No Known Activations