© 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. 117206
    Prev
    Next
    INDEX
    Explanations

    references to community and shared experiences

    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
     unlike
    -0.07
    faf
    -0.06
    achuset
    -0.06
    avier
    -0.06
     Seal
    -0.06
    EventHandler
    -0.06
    arend
    -0.06
     SEAL
    -0.06
    away
    -0.06
    Stamp
    -0.06
    POSITIVE LOGITS
     suit
    0.09
    piler
    0.07
    rava
    0.07
    imestep
    0.07
     joined
    0.07
    akan
    0.07
    Suit
    0.07
    tains
    0.07
    endir
    0.06
    ERO
    0.06
    Activations Density 0.031%

    No Known Activations