© 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. 117979
    Prev
    Next
    INDEX
    Explanations

    historical and geographical 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
    gressor
    -0.08
    ubits
    -0.07
    odash
    -0.07
    ecies
    -0.07
    /*@
    -0.07
    enties
    -0.07
    empor
    -0.07
    theon
    -0.07
    aturas
    -0.07
    ertext
    -0.07
    POSITIVE LOGITS
    800
    0.06
    772
    0.05
     Herrera
    0.05
     sve
    0.05
     parc
    0.05
     forms
    0.05
    ä»ĺãģį
    0.05
     com
    0.05
    ิà¸Ħ
    0.05
    724
    0.05
    Activations Density 0.001%

    No Known Activations