© 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. 9-LLAMASCOPE-RES-131K
    11. 98506
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their relationships to others or to events

    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
    367
    -0.07
    _VENDOR
    -0.07
    igt
    -0.06
    untary
    -0.06
    erus
    -0.06
    rive
    -0.06
    .tc
    -0.06
    irs
    -0.06
    uname
    -0.06
    sit
    -0.06
    POSITIVE LOGITS
     lantern
    0.06
    inecraft
    0.06
    _Row
    0.06
    è°±
    0.06
     Trim
    0.06
    elerin
    0.06
    ++↵
    0.06
     (++
    0.06
    Ãłng
    0.06
    enler
    0.06
    Activations Density 0.057%

    No Known Activations