© 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. 116906
    Prev
    Next
    INDEX
    Explanations

    verbs that indicate starting or initiating 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
    award
    -0.07
    имв
    -0.07
    ats
    -0.06
    asts
    -0.06
    ensch
    -0.06
    ins
    -0.06
    ráž
    -0.06
    lesia
    -0.06
    erno
    -0.06
    pu
    -0.06
    POSITIVE LOGITS
     off
    0.07
    ompiler
    0.07
     begin
    0.07
     Zucker
    0.07
     begins
    0.07
    /start
    0.07
    uther
    0.07
     rozp
    0.06
    acman
    0.06
     began
    0.06
    Activations Density 0.111%

    No Known Activations