© 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. 53808
    Prev
    Next
    INDEX
    Explanations

    references to movies and collaborations involving specific actors, particularly John Wayne and Maureen O'Hara

    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
    опиÑģ
    -0.07
    erged
    -0.07
    λÎŃον
    -0.07
    aal
    -0.06
    anzi
    -0.06
    ÐIJÑĢÑħÑĸв
    -0.06
     prostitu
    -0.06
     ******************************************************************************/↵↵
    -0.06
    izzes
    -0.06
    reach
    -0.06
    POSITIVE LOGITS
     handsome
    0.06
     tapi
    0.06
    sf
    0.06
    upal
    0.06
    çłĶ
    0.06
    807
    0.06
    835
    0.06
    817
    0.06
     indifferent
    0.06
     contract
    0.05
    Activations Density 0.002%

    No Known Activations