© 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. 61905
    Prev
    Next
    INDEX
    Explanations

    words indicating essential or highly recommended items and actions

    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
    _mA
    -0.08
    burgh
    -0.08
    ãĥ³ãĥ
    -0.08
    imbus
    -0.08
    laÄį
    -0.07
    utron
    -0.07
    umo
    -0.07
    sov
    -0.07
    ">//
    -0.07
    ickt
    -0.07
    POSITIVE LOGITS
     for
    0.08
    -in
    0.07
     regarding
    0.07
    -not
    0.06
     among
    0.06
     in
    0.06
     addition
    0.06
    -
    0.06
     amongst
    0.06
     familiar
    0.06
    Activations Density 0.003%

    No Known Activations