© 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. 63284
    Prev
    Next
    INDEX
    Explanations

    references to celebrities

    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
    á»ķ
    -0.08
    oplevel
    -0.07
     nonatomic
    -0.07
    bakan
    -0.07
    IPH
    -0.07
    ocz
    -0.07
    Âļ
    -0.07
    -ng
    -0.07
    emoc
    -0.07
    .decor
    -0.07
    POSITIVE LOGITS
     Madonna
    0.07
     AIDS
    0.07
     Indiana
    0.06
     Liber
    0.06
     HIV
    0.06
     global
    0.06
     Rochester
    0.06
     Michigan
    0.06
     (
    0.06
     disco
    0.06
    Activations Density 0.001%

    No Known Activations