© 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. 27417
    Prev
    Next
    INDEX
    Explanations

    references to companies, organizations, or individuals involved in community initiatives or efforts

    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
     rub
    -0.07
    ImageButton
    -0.07
    ynchronously
    -0.07
     –↵↵
    -0.06
    boot
    -0.06
    ilan
    -0.06
     InvalidArgumentException
    -0.06
    zie
    -0.06
    newInstance
    -0.06
    inker
    -0.06
    POSITIVE LOGITS
     already
    0.07
     interest
    0.07
     early
    0.06
     ones
    0.06
     who
    0.06
     Interest
    0.06
     intrigue
    0.06
    าะ
    0.06
    uy
    0.06
    inent
    0.06
    Activations Density 0.031%

    No Known Activations