© 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. 27758
    Prev
    Next
    INDEX
    Explanations

    topics related to the significance of animals and their roles in various 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
    wor
    -0.06
     Fon
    -0.06
    luk
    -0.06
    och
    -0.06
    ιά
    -0.06
    434
    -0.06
    ece
    -0.06
    .about
    -0.06
     submodule
    -0.06
     Loren
    -0.06
    POSITIVE LOGITS
    à¹ĥà¸Ļà¸ģาร
    0.11
    ä½ľä¸º
    0.07
     importance
    0.07
    buat
    0.07
    Ro
    0.07
    .baidu
    0.07
     pÅĻi
    0.07
     RoundedRectangle
    0.06
     regarding
    0.06
     Ro
    0.06
    Activations Density 0.104%

    No Known Activations