© 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. 9-LLAMASCOPE-RES-131K
    11. 98865
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the use of logic and rationale in discussions

    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
    aj
    -0.06
     Cob
    -0.06
    ao
    -0.06
    elles
    -0.06
    otros
    -0.06
    339
    -0.06
     truyá»ģn
    -0.06
     jel
    -0.06
    едÑĮ
    -0.05
    mediate
    -0.05
    POSITIVE LOGITS
    deen
    0.08
    ếp
    0.07
     cán
    0.07
    ermen
    0.07
    ikat
    0.07
    quet
    0.07
    ãĥĥãĥī
    0.06
     Agility
    0.06
    rnek
    0.06
    veis
    0.06
    Activations Density 0.266%

    No Known Activations