© 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. 128790
    Prev
    Next
    INDEX
    Explanations

    references to document classification and retrieval processes

    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
     standby
    -0.06
     cours
    -0.05
     Boys
    -0.05
    antha
    -0.05
     Pepper
    -0.05
    ém
    -0.05
    ascar
    -0.05
    .GetResponse
    -0.05
     dev
    -0.05
     Men
    -0.05
    POSITIVE LOGITS
    é¦Ĩ
    0.07
    atel
    0.07
    Getty
    0.07
    _ASSUME
    0.07
    SEL
    0.07
    æĭį
    0.07
    館
    0.07
    곤
    0.07
     cust
    0.07
     COPYRIGHT
    0.07
    Activations Density 0.003%

    No Known Activations