© 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. 92952
    Prev
    Next
    INDEX
    Explanations

    references to disorderly or complex situations

    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
    oya
    -0.06
    tg
    -0.06
     etc
    -0.06
     (!
    -0.06
     GetById
    -0.06
    è§Ħå®ļ
    -0.06
    etc
    -0.06
     &
    -0.06
    -0.06
     Lag
    -0.06
    POSITIVE LOGITS
    bbox
    0.07
    çak
    0.07
     mastur
    0.07
    utm
    0.07
    atra
    0.07
    kı
    0.07
    anlı
    0.07
    hlen
    0.07
    ÑĥÑĩ
    0.06
    ÅĻÃŃ
    0.06
    Activations Density 0.000%

    No Known Activations