© 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. 92591
    Prev
    Next
    INDEX
    Explanations

    greetings or salutations

    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
    nten
    -0.06
    culus
    -0.06
    /autoload
    -0.06
    ÅĻet
    -0.06
     err
    -0.06
    enu
    -0.06
    ters
    -0.06
     Giuliani
    -0.06
    eg
    -0.06
     Ferr
    -0.06
    POSITIVE LOGITS
     readers
    0.07
    大家
    0.07
     viewers
    0.07
    ãģ£ãģ±
    0.07
    .signals
    0.06
     Ott
    0.06
    ffi
    0.06
    è
    0.06
    extend
    0.06
    llx
    0.06
    Activations Density 0.007%

    No Known Activations