© 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. 81798
    Prev
    Next
    INDEX
    Explanations

    behaviors and actions related to understanding, explaining, and describing processes or concepts

    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
    442
    -0.06
    егоÑĢ
    -0.06
    684
    -0.06
    hic
    -0.06
     Kraj
    -0.06
    社
    -0.06
    696
    -0.06
    ामà¤ķ
    -0.06
     latter
    -0.06
    yan
    -0.06
    POSITIVE LOGITS
    omba
    0.09
    ãĥ¼ãĥĢ
    0.07
     situation
    0.07
    ´Ī
    0.07
    ãģªãģĹ
    0.07
    //{{
    0.07
    opor
    0.07
    bole
    0.07
     whats
    0.07
    '])?
    0.07
    Activations Density 0.041%

    No Known Activations