© 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. 92379
    Prev
    Next
    INDEX
    Explanations

    technical terms and measurements related to scientific instruments and their functions

    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
    DataExchange
    -0.08
    ühl
    -0.07
    uitka
    -0.07
    ½Ķ
    -0.07
    åĪ
    -0.07
    448
    -0.07
    ãĥ«ãĤ¯
    -0.07
    ForRow
    -0.07
     adulte
    -0.07
    caff
    -0.07
    POSITIVE LOGITS
     filter
    0.12
     filters
    0.12
    filter
    0.10
     filtering
    0.10
    Filters
    0.09
     Filter
    0.09
     Filters
    0.09
    Filter
    0.09
    (filter
    0.09
    filters
    0.09
    Activations Density 0.243%

    No Known Activations