© 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. 28204
    Prev
    Next
    INDEX
    Explanations

    dates and specific years

    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
    ä½įäºİ
    -0.08
    ä½įæĸ¼
    -0.07
     located
    -0.07
    lası
    -0.06
    efa
    -0.06
    лÑİд
    -0.06
    aphael
    -0.06
    ffa
    -0.06
     Located
    -0.06
    472
    -0.06
    POSITIVE LOGITS
    ipple
    0.07
    lingen
    0.07
    owitz
    0.07
    eways
    0.07
    ngrx
    0.07
    onomies
    0.06
    ARRIER
    0.06
    aname
    0.06
    ç¿Ķ
    0.06
    ¨ìĸ´
    0.06
    Activations Density 0.054%

    No Known Activations