© 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. 61860
    Prev
    Next
    INDEX
    Explanations

    phrases related to copyright and reproduction rights

    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
    arel
    -0.07
    zi
    -0.07
    ecycle
    -0.07
    icap
    -0.06
    teg
    -0.06
    enty
    -0.06
    gili
    -0.06
    fy
    -0.06
    issen
    -0.06
    edom
    -0.06
    POSITIVE LOGITS
     tez
    0.07
    eon
    0.07
     Pier
    0.07
     赤
    0.06
    ILA
    0.06
     zbo
    0.06
    663
    0.06
     porr
    0.06
    _advanced
    0.06
    دÙĩ
    0.06
    Activations Density 0.001%

    No Known Activations