© 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. 92164
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparisons or proximity to a reference point

    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
    urtle
    -0.07
    ei
    -0.07
    ibel
    -0.07
    iban
    -0.07
    rank
    -0.07
    /epl
    -0.07
    abelle
    -0.06
    ulton
    -0.06
    .edu
    -0.06
    opause
    -0.06
    POSITIVE LOGITS
     closest
    0.11
     close
    0.09
     clos
    0.09
     CLOSE
    0.09
    -close
    0.08
    closest
    0.08
    /close
    0.08
     proximity
    0.08
     Close
    0.08
     approximation
    0.08
    Activations Density 0.007%

    No Known Activations