© 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. 95487
    Prev
    Next
    INDEX
    Explanations

    URLs and references to online articles

    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
    atti
    -0.07
    erton
    -0.06
    wi
    -0.06
    çĭ
    -0.06
     Per
    -0.06
     Sez
    -0.06
    wie
    -0.05
    azes
    -0.05
     trunc
    -0.05
    rek
    -0.05
    POSITIVE LOGITS
    .await
    0.08
    /autoload
    0.08
    گاÙĨ
    0.08
    .styleable
    0.07
    geh
    0.07
    ationToken
    0.07
    .scalablytyped
    0.07
    沿
    0.07
    yal
    0.07
    ulta
    0.07
    Activations Density 0.006%

    No Known Activations