© 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. 121017
    Prev
    Next
    INDEX
    Explanations

    instances of the word "drag" and related terms like "drop" in various contexts

    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
    edly
    -0.09
    ariat
    -0.09
    ignum
    -0.08
    zial
    -0.08
    isers
    -0.08
    ième
    -0.08
    een
    -0.07
    ikan
    -0.07
    бом
    -0.07
    estro
    -0.07
    POSITIVE LOGITS
    ging
    0.09
    ged
    0.07
    Pull
    0.07
    nell
    0.07
    ul
    0.07
    offs
    0.07
     Pull
    0.06
    gin
    0.06
    ge
    0.06
     pull
    0.06
    Activations Density 0.004%

    No Known Activations