© 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. 40444
    Prev
    Next
    INDEX
    Explanations

    elements and attributes associated with form submissions and data descriptions

    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
     ÑĤвеÑĢд
    -0.08
     tvar
    -0.07
     actionTypes
    -0.07
    :animated
    -0.07
    onet
    -0.06
     matcher
    -0.06
    sorted
    -0.06
    Specifier
    -0.06
    odash
    -0.06
     sovere
    -0.06
    POSITIVE LOGITS
     description
    0.12
    description
    0.10
     Description
    0.10
     descriptions
    0.09
    :description
    0.09
    .description
    0.09
    _description
    0.08
     content
    0.08
    >Description
    0.08
    Description
    0.08
    Activations Density 0.042%

    No Known Activations