© 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. 120711
    Prev
    Next
    INDEX
    Explanations

    vertical bars and other symbols used in formatting

    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
    uest
    -0.07
    deo
    -0.07
    aret
    -0.06
    side
    -0.06
    ắp
    -0.06
     norm
    -0.06
    ment
    -0.06
    esters
    -0.06
     figure
    -0.06
    hn
    -0.06
    POSITIVE LOGITS
     Uncategorized
    0.10
     News
    0.07
     news
    0.07
    ooth
    0.07
    ãģŁãģĹ
    0.07
    news
    0.06
    Unc
    0.06
    .atom
    0.06
     hend
    0.06
    plen
    0.06
    Activations Density 0.002%

    No Known Activations