© 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 EvalsExportsAPI 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. 29125
    Prev
    Next
    INDEX
    Explanations

    terminology related to website development and organization

    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
    ford
    -0.07
    brig
    -0.06
     Mich
    -0.06
    pbs
    -0.06
     Král
    -0.06
    idle
    -0.06
     Olsen
    -0.06
    aban
    -0.06
    angen
    -0.06
    -await
    -0.06
    POSITIVE LOGITS
    æĸ°çļĦ
    0.08
     new
    0.07
     creation
    0.07
     новÑĭй
    0.07
    .newInstance
    0.07
    .createNew
    0.07
     нового
    0.07
    .createFrom
    0.06
     nuevas
    0.06
    ĵåIJį
    0.06
    Activations Density 0.034%

    No Known Activations