© 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. 72528
    Prev
    Next
    INDEX
    Explanations

    connections and references to various subjects or entities

    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
    .scalablytyped
    -0.09
    ellas
    -0.07
    PropertyChanged
    -0.06
    æ³Ľ
    -0.06
    åı¦
    -0.06
    iddet
    -0.06
    reau
    -0.06
     dece
    -0.06
    寧
    -0.06
     oppon
    -0.06
    POSITIVE LOGITS
    $MESS
    0.07
    /*č↵
    0.07
    aj
    0.07
    sert
    0.07
    elder
    0.07
    aro
    0.06
     Cla
    0.06
     Gron
    0.06
    erc
    0.06
    .cmd
    0.06
    Activations Density 0.071%

    No Known Activations