© 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. 62463
    Prev
    Next
    INDEX
    Explanations

    recognition and awards related to academic and artistic achievements

    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
    ersen
    -0.07
    alex
    -0.07
    ypy
    -0.06
    etas
    -0.06
     Venue
    -0.06
    oming
    -0.06
    дÑı
    -0.06
     Burke
    -0.06
    rahim
    -0.06
    воÑİ
    -0.06
    POSITIVE LOGITS
    366
    0.08
    ship
    0.07
    201
    0.07
     program
    0.07
    006
    0.07
    004
    0.07
    chaft
    0.07
    716
    0.07
    858
    0.07
     EXTRA
    0.07
    Activations Density 0.030%

    No Known Activations