© 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. 79989
    Prev
    Next
    INDEX
    Explanations

    elements related to publishing and books

    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
    readcr
    -0.07
     conven
    -0.06
    ikh
    -0.06
    ONGL
    -0.06
    ousel
    -0.06
     ki
    -0.06
    elfast
    -0.06
     textual
    -0.06
    ensis
    -0.06
     equival
    -0.05
    POSITIVE LOGITS
    лини
    0.07
    λεκ
    0.07
    (æ°´
    0.07
    ëĮ
    0.07
    ovan
    0.07
    RAP
    0.07
    IMO
    0.07
    longleftrightarrow
    0.07
     обÑĢа
    0.07
    /gui
    0.07
    Activations Density 0.000%

    No Known Activations