© 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. 55220
    Prev
    Next
    INDEX
    Explanations

    phrases indicating suitability or appropriateness for various contexts

    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
     behalf
    -0.08
    redient
    -0.07
    lÃŃÄį
    -0.07
    UIL
    -0.07
    UME
    -0.07
    quisition
    -0.07
    ekt
    -0.07
     exem
    -0.06
     ÄIJÃło
    -0.06
    -lite
    -0.06
    POSITIVE LOGITS
     use
    0.10
     purpose
    0.06
    Persons
    0.06
    268
    0.06
    à¸Ļาà¸Ļ
    0.06
     consideration
    0.06
    aylor
    0.06
     being
    0.06
     Persons
    0.06
    iji
    0.06
    Activations Density 0.024%

    No Known Activations