© 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. 105359
    Prev
    Next
    INDEX
    Explanations

    HTML link attributes

    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
    owell
    -0.08
    ÑĢÑĥÑĤ
    -0.06
     Merk
    -0.06
     Guill
    -0.06
    alat
    -0.05
    á»ĵ
    -0.05
    864
    -0.05
    enth
    -0.05
     cort
    -0.05
    /embed
    -0.05
    POSITIVE LOGITS
    ervlet
    0.07
    sÃŃ
    0.07
    оÑĩно
    0.07
    μμα
    0.07
    禮
    0.07
    _Anim
    0.06
    LineStyle
    0.06
    _ABC
    0.06
    .radioButton
    0.06
    è¿Ķ
    0.06
    Activations Density 0.001%

    No Known Activations