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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 87068
    Prev
    Next
    INDEX
    Explanations

    quantifiable measurements or numerical data in the text

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

    Section or entry headings that introduce new topics in reference materials, guides, or catalogs, often followed by explanatory 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
    ιÏİν
    -0.07
    ternet
    -0.06
    allel
    -0.06
     Gould
    -0.05
    Ã
    -0.05
    ableObject
    -0.05
    gnore
    -0.05
    debit
    -0.05
    enger
    -0.05
    iggers
    -0.05
    POSITIVE LOGITS
    uts
    0.08
    reeze
    0.07
    ủ
    0.07
    ìļ¸
    0.06
    onis
    0.06
    âĢı
    0.06
    oldt
    0.06
    _IV
    0.06
    roperties
    0.06
    ائÙħ
    0.06
    Activations Density 0.057%

    No Known Activations