© 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. 89438
    Prev
    Next
    INDEX
    Explanations

    references to downloadable content or associated files

    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
    avenport
    -0.07
     volta
    -0.06
    ยา
    -0.06
    eyh
    -0.06
    (.
    -0.06
    ota
    -0.06
    ason
    -0.06
     Vic
    -0.06
     Finish
    -0.06
    odable
    -0.06
    POSITIVE LOGITS
    alon
    0.07
    llen
    0.06
     Sof
    0.06
    iji
    0.06
    خش
    0.06
     ><?
    0.06
    ackers
    0.06
    ãĥĦ
    0.06
    Convertible
    0.06
    jer
    0.06
    Activations Density 0.000%

    No Known Activations