© 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. 62606
    Prev
    Next
    INDEX
    Explanations

    references to titles, honors, or recognitions associated with individuals

    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
    naires
    -0.07
    dfd
    -0.07
     unfavor
    -0.07
    lias
    -0.07
    antics
    -0.07
    esimal
    -0.06
    anie
    -0.06
    eme
    -0.06
    licate
    -0.06
    agos
    -0.06
    POSITIVE LOGITS
     Lords
    0.07
    Lord
    0.07
     Lord
    0.07
    lington
    0.06
     lord
    0.06
    ccoli
    0.06
    iev
    0.06
    ilden
    0.06
     bulk
    0.06
    oldemort
    0.06
    Activations Density 0.009%

    No Known Activations