© 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 EvalsExportsAPI 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. 77115
    Prev
    Next
    INDEX
    Explanations

    references to various institutes and organizations involved in research and education

    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
    _Tis
    -0.07
     Ðĵолов
    -0.07
    θο
    -0.07
    .Foundation
    -0.06
    inea
    -0.06
     justification
    -0.06
    _MetaData
    -0.06
    -roll
    -0.06
    azer
    -0.06
     výsled
    -0.06
    POSITIVE LOGITS
     canv
    0.06
    .promise
    0.06
    otal
    0.06
    utsch
    0.06
    mate
    0.06
    inde
    0.06
    BLE
    0.06
     Buccane
    0.06
    (Of
    0.06
    ĶĦ
    0.06
    Activations Density 0.011%

    No Known Activations