© 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. 124441
    Prev
    Next
    INDEX
    Explanations

    punctuation or sentence endings

    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
     Sas
    -0.08
    iph
    -0.08
    ivol
    -0.07
    RESOURCE
    -0.07
    ipay
    -0.07
     Sanayi
    -0.07
    (æľ¨
    -0.06
    _PTR
    -0.06
    urgeon
    -0.06
    /Gate
    -0.06
    POSITIVE LOGITS
    ler
    0.07
    ениÑİ
    0.06
     Rowe
    0.06
    abei
    0.06
    ĺħ
    0.06
    apy
    0.06
    ominator
    0.06
    æĿ¯
    0.06
    inium
    0.06
     dipping
    0.06
    Activations Density 0.000%

    No Known Activations