© 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. 123326
    Prev
    Next
    INDEX
    Explanations

    instances of the word "one" and related phrases

    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
    erdale
    -0.09
    ruba
    -0.08
     же
    -0.08
    à¸ĩาà¸Ļ
    -0.07
    OSE
    -0.07
    ÑĦик
    -0.07
    usable
    -0.07
    afür
    -0.07
     Others
    -0.07
    esson
    -0.07
    POSITIVE LOGITS
    ologically
    0.07
    ìłĪ
    0.06
     Gent
    0.06
    IDA
    0.06
    ially
    0.06
    ëĭ¤ê°Ģ
    0.06
    ida
    0.05
    879
    0.05
    istically
    0.05
    arily
    0.05
    Activations Density 0.007%

    No Known Activations