© 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. 40127
    Prev
    Next
    INDEX
    Explanations

    references to awards, schools, and legislation

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

    Text describing how people, places, awards, or institutions were named after specific individuals or concepts, often providing attribution context.

    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
    ate
    -0.06
    LoginForm
    -0.06
     rack
    -0.05
    eren
    -0.05
    trand
    -0.05
    elling
    -0.05
    esta
    -0.05
    creenshot
    -0.05
    ulia
    -0.05
    oling
    -0.05
    POSITIVE LOGITS
     named
    0.31
    named
    0.30
     Named
    0.28
    Named
    0.26
    _named
    0.20
     name
    0.20
     naming
    0.19
    .named
    0.19
    (named
    0.18
     names
    0.18
    Activations Density 0.128%

    No Known Activations