© 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. 121358
    Prev
    Next
    INDEX
    Explanations

    specific references to activities or events involving a group or collaboration

    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
     actionTypes
    -0.07
     Pods
    -0.06
    bsolute
    -0.06
     darm
    -0.06
     Web
    -0.06
    ÙĴ
    -0.06
    469
    -0.06
    ify
    -0.06
    ottes
    -0.06
    anny
    -0.06
    POSITIVE LOGITS
    ahi
    0.07
    OfType
    0.07
    ERM
    0.06
     Gow
    0.06
    rak
    0.06
     Freund
    0.06
     ones
    0.06
    SetColor
    0.06
     hi
    0.06
    aben
    0.06
    Activations Density 0.000%

    No Known Activations