© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 1441
    Prev
    Next
    INDEX
    Explanations

    actions that suggest enhancement or modification processes

    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
    üç
    -0.06
    icking
    -0.06
    nell
    -0.06
    isz
    -0.06
    ys
    -0.06
    <::
    -0.06
    /display
    -0.06
    rysler
    -0.06
    gis
    -0.06
    hold
    -0.06
    POSITIVE LOGITS
    asca
    0.07
    ä¸Ģä¸ĭ
    0.07
    ếp
    0.07
    ardi
    0.07
    asics
    0.07
    omens
    0.06
    èħ
    0.06
    rava
    0.06
    Ñİ
    0.06
    croft
    0.06
    Activations Density 0.038%

    No Known Activations