© 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. 17-LLAMASCOPE-RES-131K
    11. 27701
    Prev
    Next
    INDEX
    Explanations

    keywords and symbols related to programming and build processes

    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
    //{{
    -0.08
    olini
    -0.07
    alach
    -0.07
    elson
    -0.07
    alis
    -0.07
    ubi
    -0.07
    ichtig
    -0.06
    artment
    -0.06
     TextAlign
    -0.06
    zek
    -0.06
    POSITIVE LOGITS
    odore
    0.07
    uka
    0.07
     autogenerated
    0.07
    !=(
    0.06
    .webkit
    0.06
    /../
    0.06
    ars
    0.06
     Lore
    0.06
    axe
    0.06
    产
    0.06
    Activations Density 0.001%

    No Known Activations