© 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. 1189
    Prev
    Next
    INDEX
    Explanations

    the name "Joe" and its variations, indicating a focus on this specific individual's prevalence or importance

    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
    rous
    -0.08
    IDEO
    -0.07
    naire
    -0.07
    ness
    -0.07
    rites
    -0.07
    ne
    -0.07
    eshire
    -0.07
    RITE
    -0.07
    UPPORT
    -0.07
     CONSEQUENTIAL
    -0.07
    POSITIVE LOGITS
     Biden
    0.08
    ys
    0.07
    ÌĪ
    0.07
    çıŃ
    0.06
    bidden
    0.06
    à¯įà®
    0.06
    suit
    0.06
    lbrace
    0.06
    Ùģس
    0.06
    fraction
    0.06
    Activations Density 0.008%

    No Known Activations