© 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. 129321
    Prev
    Next
    INDEX
    Explanations

    instances of specific product names or categories

    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
    ary
    -0.07
    ÑĤÑı
    -0.06
     pans
    -0.06
    çŃĨ
    -0.06
    íİ
    -0.05
    nt
    -0.05
    Interop
    -0.05
    ARED
    -0.05
    itas
    -0.05
    NT
    -0.05
    POSITIVE LOGITS
    chedulers
    0.09
    kiye
    0.07
    ruž
    0.07
    agua
    0.07
    COLUMN
    0.07
    beiten
    0.07
    PermissionsResult
    0.07
    ĺIJ
    0.07
    ="__
    0.07
    lescope
    0.07
    Activations Density 0.000%

    No Known Activations