© 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. 40476
    Prev
    Next
    INDEX
    Explanations

    technical terms and error messages related to programming and system configurations

    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
    ourt
    -0.07
    Exposed
    -0.06
    udiantes
    -0.06
    ë¶Ī
    -0.06
    _ball
    -0.06
    OUCH
    -0.06
    EDIA
    -0.06
     apl
    -0.06
    zek
    -0.06
    avan
    -0.06
    POSITIVE LOGITS
    undefined
    0.08
    .undefined
    0.07
    leigh
    0.06
    anity
    0.06
    unknown
    0.06
     undefined
    0.06
     Hakk
    0.06
    egin
    0.06
    %E
    0.06
    LING
    0.06
    Activations Density 0.032%

    No Known Activations