© 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. 124451
    Prev
    Next
    INDEX
    Explanations

    references to files and image processing components

    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
     recharge
    -0.06
     necessary
    -0.06
     Tate
    -0.05
     receiving
    -0.05
     Saudis
    -0.05
    kan
    -0.05
    ares
    -0.05
     Dia
    -0.05
    007
    -0.05
     ole
    -0.05
    POSITIVE LOGITS
    ContentLoaded
    0.08
    presso
    0.08
    .readString
    0.08
    ternet
    0.08
    ileo
    0.08
    isay
    0.07
    ór
    0.07
    auses
    0.07
    Into
    0.07
    ymous
    0.07
    Activations Density 0.035%

    No Known Activations