© 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. 15-LLAMASCOPE-RES-131K
    11. 90063
    Prev
    Next
    INDEX
    Explanations

    words related to classifications and social labels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Words and phrases that could trigger context-specific interpretations, including place names, technical terminology, idioms, and potentially sensitive content.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    ried
    -0.08
    èĥĨ
    -0.07
    ÑĢеÑĤ
    -0.07
    reta
    -0.07
    erif
    -0.06
    reib
    -0.06
    cri
    -0.06
    obb
    -0.06
     num
    -0.06
    iska
    -0.06
    POSITIVE LOGITS
     instead
    0.08
    instead
    0.07
    #
    0.07
    å¸Ń
    0.07
     Renders
    0.07
     geil
    0.07
     männer
    0.07
    ÙĪزÙĩ
    0.07
     versus
    0.06
    pike
    0.06
    Activations Density 0.016%

    No Known Activations