© 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. 71159
    Prev
    Next
    INDEX
    Explanations

    mentions of gender inequality and stereotypes

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

    Demarcation points between different content entries or articles, typically following a "more" or "read more" prompt and preceding new unrelated 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
     hete
    -0.09
     dilig
    -0.08
    .Management
    -0.07
    znam
    -0.07
    ,↵↵↵↵
    -0.07
    ÑĨвеÑĤ
    -0.07
    ÏĬ
    -0.07
    eniable
    -0.07
    incoming
    -0.07
    âĢ¦.↵↵
    -0.07
    POSITIVE LOGITS
    ालत
    0.07
     Zum
    0.06
    coli
    0.06
    {}{↵
    0.06
    aska
    0.06
    than
    0.06
     Swe
    0.06
     Mig
    0.06
    /gtest
    0.06
    elic
    0.05
    Activations Density 0.163%

    No Known Activations