© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 90486
    Prev
    Next
    INDEX
    Explanations

    references to external resources or functions

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

    Tokens that appear at boundaries between questions and answers in technical discussions, often marking the end of code snippets or queries.

    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
    ennai
    -0.08
    .gdx
    -0.07
    .getOwnProperty
    -0.06
    uro
    -0.06
    Ñıд
    -0.06
    radient
    -0.06
    że
    -0.06
    izzlies
    -0.06
    criptors
    -0.05
     lig
    -0.05
    POSITIVE LOGITS
     Answer
    0.08
    çŃĶæ¡Ī
    0.08
     answer
    0.08
     answered
    0.08
     Ans
    0.07
    answer
    0.07
     solution
    0.07
    .answer
    0.07
    solution
    0.07
     ANSW
    0.07
    Activations Density 0.013%

    No Known Activations