© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 27333
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or events

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

    Titles or section headings that appear before content sections on webpages, articles, or publications, often representing navigation elements or content dividers.

    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
    yne
    -0.06
    ↵
    -0.06
    ÄĽ
    -0.06
    обÑĢаз
    -0.06
     flo
    -0.06
     inc
    -0.06
     sert
    -0.05
     fore
    -0.05
     for
    -0.05
    adle
    -0.05
    POSITIVE LOGITS
    ErrorException
    0.08
    ------+------+
    0.07
    祥
    0.07
    _perms
    0.07
    ]={↵
    0.07
    αιδ
    0.07
    venir
    0.07
    .bunifuFlatButton
    0.07
    udo
    0.07
    inton
    0.07
    Activations Density 0.050%

    No Known Activations