© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 18783
    Prev
    Next
    INDEX
    Explanations

    code-related imports and class declarations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    /lic
    -0.07
    .Middle
    -0.06
    adder
    -0.06
    plib
    -0.06
    .weixin
    -0.06
    acades
    -0.06
    edis
    -0.06
    /licenses
    -0.06
    ochen
    -0.06
    è«
    -0.06
    POSITIVE LOGITS
    oba
    0.07
    gage
    0.07
    ikip
    0.07
    ÛĮزÛĮ
    0.07
    ome
    0.06
    pedia
    0.06
     Podesta
    0.06
     Executes
    0.06
    .scalablytyped
    0.06
    gel
    0.06
    Activations Density 0.000%

    No Known Activations