© 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. 95856
    Prev
    Next
    INDEX
    Explanations

    complex terms related to programming or technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ges
    -0.07
    estre
    -0.07
    liv
    -0.06
    atories
    -0.06
    .Parse
    -0.06
    tement
    -0.06
    soles
    -0.06
     hood
    -0.06
    ential
    -0.06
    INGS
    -0.06
    POSITIVE LOGITS
     you
    0.07
     yourself
    0.07
    hsi
    0.07
    «a
    0.07
    óż
    0.07
     hãy
    0.07
    айÑĤе
    0.07
    rek
    0.06
    eger
    0.06
    iere
    0.06
    Activations Density 0.026%

    No Known Activations