© 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. 61802
    Prev
    Next
    INDEX
    Explanations

    terms associated with advanced computing and data processing concepts

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

    Technical terminology elements that represent specialized components, programming variables, or domain-specific modifiers in scientific, computing, and professional contexts.

    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
     noqa
    -0.07
    ãĥ¬ãĥ¼
    -0.06
    èĢĥ
    -0.06
    ymbols
    -0.06
    indsight
    -0.06
    orde
    -0.06
    ↵
    -0.05
     breath
    -0.05
    å°Ĩ
    -0.05
    antium
    -0.05
    POSITIVE LOGITS
    Touches
    0.07
    vÄĽt
    0.07
    #af
    0.07
    STITUTE
    0.07
    _sprites
    0.07
    \admin
    0.07
    ÙĦÙĥتر
    0.07
    ripe
    0.07
    ê·ł
    0.07
    seat
    0.06
    Activations Density 0.649%

    No Known Activations