© 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. 15380
    Prev
    Next
    INDEX
    Explanations

    references to images or pictures in the 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
    ierre
    -0.07
    lew
    -0.06
    ledon
    -0.06
    umer
    -0.06
    ants
    -0.06
    ophy
    -0.06
    ongyang
    -0.06
    ìĪł
    -0.06
    uchar
    -0.06
    ibus
    -0.06
    POSITIVE LOGITS
     taken
    0.08
    taken
    0.07
     Taken
    0.07
    Taken
    0.07
     example
    0.07
    ån
    0.07
     examples
    0.06
     모ìĬµ
    0.06
    ADX
    0.06
    ká
    0.06
    Activations Density 0.009%

    No Known Activations