© 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. 72294
    Prev
    Next
    INDEX
    Explanations

    references to specific articles or publications

    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
    oret
    -0.06
    ERT
    -0.06
    ertainment
    -0.06
    Wer
    -0.06
    vert
    -0.05
    apos
    -0.05
    okud
    -0.05
     Vor
    -0.05
    ůr
    -0.05
     Wer
    -0.05
    POSITIVE LOGITS
    ewire
    0.08
     ÑģайÑĤе
    0.07
    unsch
    0.07
    fono
    0.07
     website
    0.07
    emean
    0.07
    ãģĸ
    0.07
    å¦Ĥä½ķ
    0.07
    enef
    0.07
    reu
    0.07
    Activations Density 0.028%

    No Known Activations