© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 107990
    Prev
    Next
    INDEX
    Explanations

    negative sentiments or critiques related to photography and art experiences

    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
    _fonts
    -0.07
    indle
    -0.07
    onden
    -0.07
    issions
    -0.07
    ported
    -0.07
    odus
    -0.06
    ESSAGES
    -0.06
    HeaderCode
    -0.06
    eya
    -0.06
    Intialized
    -0.06
    POSITIVE LOGITS
     Tig
    0.06
    CurrentValue
    0.06
    LAY
    0.06
    nga
    0.06
     беÑĢез
    0.06
    -thumb
    0.06
    ummy
    0.06
     bol
    0.06
     partly
    0.06
     occasional
    0.06
    Activations Density 0.008%

    No Known Activations