© 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. 103993
    Prev
    Next
    INDEX
    Explanations

    programming-related commands or syntax elements

    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
    ãĥĭãĥĥãĤ¯
    -0.07
    kehr
    -0.07
    iqueta
    -0.06
    ÑĦиÑĨи
    -0.06
     Misc
    -0.06
    usch
    -0.06
    tered
    -0.06
    ÑĥÑģÑĤа
    -0.06
    atem
    -0.06
    misc
    -0.06
    POSITIVE LOGITS
    uce
    0.08
     Sith
    0.07
     ê·¸ëłĩ
    0.06
    goto
    0.06
     Operand
    0.06
    ToDo
    0.06
    else
    0.06
     goto
    0.06
    elif
    0.06
    951
    0.06
    Activations Density 0.000%

    No Known Activations