© 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 EvalsExportsAPI 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. 119243
    Prev
    Next
    INDEX
    Explanations

    references to academic or professional conferences and related activities

    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
     variety
    -0.07
    igt
    -0.06
     Humph
    -0.06
    ä¿Ĭ
    -0.06
     Uhr
    -0.06
    à¥Ģश
    -0.06
    izm
    -0.06
    amak
    -0.06
    ÑĩаÑĤ
    -0.06
    lot
    -0.06
    POSITIVE LOGITS
     nÃły
    0.09
    DDD
    0.08
    é¦ĸ
    0.07
    ocrat
    0.07
    ytut
    0.07
    δα
    0.06
    ikk
    0.06
    onaut
    0.06
    icer
    0.06
    ¤ij
    0.06
    Activations Density 0.079%

    No Known Activations