© 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. 80933
    Prev
    Next
    INDEX
    Explanations

    references to reports and agreements related to data and organizational structures

    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
    ruba
    -0.07
     sticking
    -0.06
     xong
    -0.06
    rang
    -0.06
     forts
    -0.06
    uce
    -0.06
    oren
    -0.06
     èµ·
    -0.06
    cher
    -0.06
     Sb
    -0.06
    POSITIVE LOGITS
     which
    0.11
    which
    0.10
     recently
    0.09
    Which
    0.08
    recent
    0.07
     WHICH
    0.07
    Recent
    0.07
     Recent
    0.07
    Äįen
    0.07
     Which
    0.07
    Activations Density 0.056%

    No Known Activations