© 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. 53824
    Prev
    Next
    INDEX
    Explanations

    lists and collections of recommended resources

    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
     Forums
    -0.07
    statt
    -0.07
    ело
    -0.07
    /ajax
    -0.07
    lobals
    -0.07
    lander
    -0.07
    halten
    -0.06
    örü
    -0.06
     pParent
    -0.06
    isoft
    -0.06
    POSITIVE LOGITS
     list
    0.14
     recommendations
    0.12
     selection
    0.11
     picks
    0.11
     List
    0.11
    list
    0.10
     lists
    0.10
     selections
    0.10
    Selection
    0.10
     Selection
    0.10
    Activations Density 0.043%

    No Known Activations