© 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. 9-LLAMASCOPE-RES-131K
    11. 97594
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
    &M
    -0.06
    anych
    -0.06
    noch
    -0.06
    bero
    -0.06
    illi
    -0.06
    anc
    -0.05
     Acid
    -0.05
    yal
    -0.05
    ilk
    -0.05
    84
    -0.05
    POSITIVE LOGITS
    ypi
    0.08
    liš
    0.07
    æķ
    0.07
     giỼi
    0.07
     LIC
    0.07
    IRE
    0.06
    ôi
    0.06
    ç¨
    0.06
    assage
    0.06
    EIF
    0.06
    Activations Density 0.000%

    No Known Activations