© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71717
    Prev
    Next
    INDEX
    Explanations

    questions and requests for calculations or definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    bane
    -0.07
    EMPLARY
    -0.07
    alet
    -0.07
    figcaption
    -0.06
    biz
    -0.06
    chts
    -0.06
    çķ
    -0.06
     تاب
    -0.06
    onders
    -0.06
     Gazette
    -0.06
    POSITIVE LOGITS
     expected
    0.07
    igit
    0.07
     ************************************************
    0.06
    ế
    0.06
    expected
    0.06
     expect
    0.06
     alternate
    0.06
     corresponding
    0.06
    اشت
    0.06
     Ekon
    0.06
    Activations Density 0.019%

    No Known Activations