© 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. 28099
    Prev
    Next
    INDEX
    Explanations

    words associated with interaction or response in various contexts

    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
    гал
    -0.07
    айÑĤ
    -0.07
    .Override
    -0.07
    .Toggle
    -0.07
    Ñĥки
    -0.07
     пÑĢоÑĩ
    -0.07
    &_
    -0.07
    моÑĤ
    -0.07
    vant
    -0.07
    agged
    -0.07
    POSITIVE LOGITS
    iously
    0.06
    esel
    0.06
    0.06
    utin
    0.06
    eking
    0.06
    obuf
    0.06
    ute
    0.06
    irs
    0.05
    453
    0.05
    ifax
    0.05
    Activations Density 0.039%

    No Known Activations