© 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. 17-LLAMASCOPE-RES-131K
    11. 70822
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics in a document

    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
     Mic
    -0.06
    etcode
    -0.06
    ril
    -0.05
    spiel
    -0.05
     mic
    -0.05
    arel
    -0.05
    ulatory
    -0.05
    icap
    -0.05
     Raphael
    -0.05
    atches
    -0.05
    POSITIVE LOGITS
    /cgi
    0.07
    anmar
    0.07
    imas
    0.07
    colo
    0.07
    asics
    0.07
    agra
    0.07
    PTY
    0.07
    onus
    0.06
    essim
    0.06
     traction
    0.06
    Activations Density 0.000%

    No Known Activations