© 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. 81865
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a continuous state or duration of time

    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
    eria
    -0.07
    usted
    -0.07
    mtree
    -0.07
    late
    -0.07
    è´¨
    -0.07
    .Interop
    -0.07
    ses
    -0.07
    positor
    -0.06
    tsky
    -0.06
    chester
    -0.06
    POSITIVE LOGITS
    forth
    0.08
    LY
    0.07
    éré
    0.07
    ;y
    0.07
    jÅ¡ÃŃ
    0.06
    larg
    0.06
     ëĤ´ëł¤
    0.06
    atk
    0.06
    879
    0.06
     become
    0.06
    Activations Density 0.003%

    No Known Activations