© 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. 54117
    Prev
    Next
    INDEX
    Explanations

    code comments or documentation sections, indicating programming or technical content

    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
    eron
    -0.07
     nuest
    -0.07
    ies
    -0.06
    åĨ²
    -0.06
    ();)
    -0.06
     )↵↵↵↵↵↵↵↵
    -0.06
    eva
    -0.06
    .python
    -0.06
    /Private
    -0.06
    entanyl
    -0.06
    POSITIVE LOGITS
    amat
    0.08
    akov
    0.07
    Albert
    0.06
    maze
    0.06
    uppe
    0.06
    -metadata
    0.06
    argins
    0.06
    981
    0.06
    /vnd
    0.06
     Lib
    0.06
    Activations Density 0.000%

    No Known Activations