© 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. 120562
    Prev
    Next
    INDEX
    Explanations

    punctuation or formatting elements in text

    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
    iveau
    -0.07
     Ñģад
    -0.07
     ná
    -0.07
     Ná
    -0.07
    ovel
    -0.07
    audi
    -0.07
     Ãĩev
    -0.07
    uder
    -0.07
    elan
    -0.07
     ayn
    -0.07
    POSITIVE LOGITS
    ëĿ¼ëĬĶ
    0.08
    atto
    0.06
    ubern
    0.06
    .tt
    0.06
     adlı
    0.06
     olmak
    0.06
     Rogers
    0.06
    ãģ¨ãģĦãģĨ
    0.05
    zer
    0.05
    cz
    0.05
    Activations Density 0.024%

    No Known Activations