© 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. 108341
    Prev
    Next
    INDEX
    Explanations

    specific numerical data and evidence related to claims or analysis

    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
    ube
    -0.08
    accion
    -0.07
    ãĥ¼ãĤ¸
    -0.06
    akh
    -0.06
    cean
    -0.06
    afs
    -0.06
    ubi
    -0.06
    inger
    -0.06
    à¸Ĺร
    -0.06
    eam
    -0.06
    POSITIVE LOGITS
     impression
    0.09
     rise
    0.08
     preference
    0.08
     kepada
    0.07
    thumbs
    0.07
     thumbs
    0.07
     directions
    0.07
    äºĪ
    0.07
     away
    0.07
     precedence
    0.07
    Activations Density 0.181%

    No Known Activations