© 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. 9-LLAMASCOPE-RES-131K
    11. 98321
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "curl"

    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
    adal
    -0.07
     redund
    -0.06
    empl
    -0.06
    elah
    -0.06
    sth
    -0.06
     redundant
    -0.06
    aos
    -0.06
    ãģ¦ãĤĭ
    -0.06
    oyo
    -0.06
    irim
    -0.06
    POSITIVE LOGITS
    ismus
    0.08
    urette
    0.07
    à¤Ĩर
    0.07
    ãĥĨãĥ«
    0.07
    _setopt
    0.07
    -thumbnails
    0.07
    hsi
    0.07
    ÅĻÃŃzenÃŃ
    0.07
    beck
    0.07
    ÂŃing
    0.06
    Activations Density 0.000%

    No Known Activations