© 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. 61939
    Prev
    Next
    INDEX
    Explanations

    instances of the word "let."

    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
    ÅĤad
    -0.07
    ogle
    -0.06
    ÑĭÑģ
    -0.06
    asthan
    -0.06
    ULA
    -0.06
    RP
    -0.06
    ula
    -0.06
    oenix
    -0.06
    enna
    -0.06
     Horton
    -0.06
    POSITIVE LOGITS
    ting
    0.09
    tings
    0.08
    itore
    0.07
     Glob
    0.07
    ноÑģи
    0.06
     Payne
    0.06
    pedia
    0.06
    ts
    0.06
    nici
    0.06
    jos
    0.06
    Activations Density 0.008%

    No Known Activations