© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4118
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "for"

    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
    omit
    -0.07
    عÙħ
    -0.07
    à¸ķ
    -0.06
    jour
    -0.06
    iliki
    -0.06
    ÏĢιÏĥ
    -0.06
     actionTypes
    -0.06
    ivre
    -0.06
    ulton
    -0.06
    515
    -0.06
    POSITIVE LOGITS
     bol
    0.07
     OE
    0.07
     Tun
    0.07
     Bol
    0.07
    EFI
    0.07
     Performance
    0.07
    affen
    0.07
    stup
    0.07
     EFI
    0.07
     Wilkinson
    0.07
    Activations Density 0.000%

    No Known Activations