© 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. 61768
    Prev
    Next
    INDEX
    Explanations

    information related to community events, opportunities, and health-related topics

    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
     tat
    -0.06
    ,
    -0.06
    rell
    -0.05
    WithEmail
    -0.05
    .svg
    -0.05
     Cant
    -0.05
    άνÏī
    -0.05
     elegant
    -0.05
    .mask
    -0.05
    borne
    -0.05
    POSITIVE LOGITS
     part
    0.12
     ÑĢамкаÑħ
    0.11
     جزء
    0.11
     ÑĩаÑģÑĤÑĮ
    0.10
     courtesy
    0.10
     souÄįást
    0.10
     souÄįástÃŃ
    0.09
     μÎŃÏģοÏĤ
    0.09
    cour
    0.09
    part
    0.09
    Activations Density 0.073%

    No Known Activations