© 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. 18247
    Prev
    Next
    INDEX
    Explanations

    the concept of distance or how far something is

    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
    dings
    -0.07
    busters
    -0.06
    chter
    -0.06
    ius
    -0.06
    ADER
    -0.06
    .scalablytyped
    -0.06
    chaft
    -0.06
    chor
    -0.06
    chai
    -0.06
    ownt
    -0.06
    POSITIVE LOGITS
    thest
    0.11
    -reaching
    0.11
    away
    0.09
     away
    0.08
    mland
    0.07
    rier
    0.07
    /close
    0.07
     khá»ıi
    0.07
     fetched
    0.07
     removed
    0.07
    Activations Density 0.023%

    No Known Activations