© 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. 82621
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their contextual importance within the text

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

    Text appearing at content boundaries, typically indicating the end of one section before transitioning to new 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
    hall
    -0.07
    [Unit
    -0.07
    aday
    -0.06
    enheim
    -0.06
    -addons
    -0.06
    472
    -0.06
    γÏī
    -0.06
    evenodd
    -0.06
    ch
    -0.06
    593
    -0.06
    POSITIVE LOGITS
    oreach
    0.07
    ä¸Ģ页
    0.07
     <↵
    0.07
    аÑĢÑĩ
    0.07
    ersiz
    0.07
    .gf
    0.07
    ameda
    0.07
    tah
    0.06
    essenger
    0.06
    cpy
    0.06
    Activations Density 0.013%

    No Known Activations