© 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. 117197
    Prev
    Next
    INDEX
    Explanations

    specialized terminology related to academic or technical subjects

    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
    ourg
    -0.08
     Modular
    -0.07
    enko
    -0.07
     modular
    -0.06
    ÑĩаÑģ
    -0.06
    /add
    -0.06
    com
    -0.06
    assel
    -0.06
    q
    -0.06
    Cached
    -0.06
    POSITIVE LOGITS
    FTA
    0.07
    .visitMethod
    0.07
    ahir
    0.06
     authDomain
    0.06
    enumerator
    0.06
    aurus
    0.06
    ajor
    0.06
    /gtest
    0.06
    catid
    0.06
     ton
    0.06
    Activations Density 0.002%

    No Known Activations