© 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. 77271
    Prev
    Next
    INDEX
    Explanations

    discussions about variations in terminology and their implications

    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
    oldem
    -0.08
    Touches
    -0.07
    idle
    -0.07
    ostel
    -0.07
    Translated
    -0.07
    KANJI
    -0.06
    translation
    -0.06
    hsi
    -0.06
    -Language
    -0.06
    osl
    -0.06
    POSITIVE LOGITS
     usage
    0.11
     Usage
    0.10
    Usage
    0.10
     USAGE
    0.09
    _usage
    0.08
    usage
    0.08
    USAGE
    0.07
     ноÑĢмаÑĤив
    0.07
    .usage
    0.07
     ayn
    0.06
    Activations Density 0.010%

    No Known Activations