© 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. 38948
    Prev
    Next
    INDEX
    Explanations

    discussions related to scientific methodologies and the nature of research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Transitional phrases and explanatory language that connect or clarify complex concepts, particularly in technical or instructional text.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    UGC
    -0.07
    onica
    -0.06
    ē
    -0.06
    868
    -0.06
    lep
    -0.06
    .toHexString
    -0.06
    Ń
    -0.06
    Ñĭл
    -0.06
    @js
    -0.06
     polis
    -0.06
    POSITIVE LOGITS
     myself
    0.07
     Await
    0.07
    ronics
    0.07
    dsn
    0.06
    ĵåIJį
    0.06
     explanations
    0.06
    bero
    0.06
    incerely
    0.06
    acia
    0.06
     baiser
    0.06
    Activations Density 0.060%

    No Known Activations