© 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. 78504
    Prev
    Next
    INDEX
    Explanations

    numerically expressed quantities or statistical data

    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
    az
    -0.07
    ergy
    -0.06
    thy
    -0.06
    urf
    -0.06
    406
    -0.06
    acl
    -0.06
     Thy
    -0.06
     fare
    -0.06
     Ban
    -0.06
    lm
    -0.06
    POSITIVE LOGITS
    ÑĪÑĤов
    0.06
    imir
    0.06
    rale
    0.06
    »
    0.06
    Cheap
    0.06
    elling
    0.06
    ErrorException
    0.06
    Ñıж
    0.06
    andler
    0.06
    ιβ
    0.06
    Activations Density 0.005%

    No Known Activations