© 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. 17951
    Prev
    Next
    INDEX
    Explanations

    references to specific years

    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
    tach
    -0.07
    ngo
    -0.07
    eco
    -0.06
    Ư
    -0.06
    ãĥ¼ãĥĸ
    -0.06
    .Library
    -0.06
    pecially
    -0.06
    ãĥŁãĥ¥
    -0.06
    avra
    -0.06
    911
    -0.06
    POSITIVE LOGITS
    /inet
    0.07
    shot
    0.07
    _framework
    0.07
    PointerException
    0.06
    isko
    0.06
    wal
    0.06
    lasses
    0.06
    .UnitTesting
    0.06
    idden
    0.06
    hani
    0.06
    Activations Density 0.051%

    No Known Activations