© 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. 39354
    Prev
    Next
    INDEX
    Explanations

    references to specific institutions or organizations

    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
    irst
    -0.07
    oose
    -0.07
    erals
    -0.07
    imal
    -0.07
    BERS
    -0.07
    apa
    -0.07
    úc
    -0.07
    letic
    -0.07
    acey
    -0.07
     CircularProgress
    -0.07
    POSITIVE LOGITS
    ance
    0.10
    antly
    0.10
    ant
    0.09
    ino
    0.08
    unce
    0.07
    ances
    0.07
    afen
    0.07
    uate
    0.07
    ingly
    0.07
    land
    0.07
    Activations Density 0.006%

    No Known Activations