© 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. 41572
    Prev
    Next
    INDEX
    Explanations

    formal mathematical definitions and properties, particularly concerning graphs and set theory

    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
    onders
    -0.07
    enne
    -0.07
    tah
    -0.06
    ahy
    -0.06
    otte
    -0.06
     Piet
    -0.06
    byname
    -0.06
    lay
    -0.06
    nett
    -0.06
    emmel
    -0.06
    POSITIVE LOGITS
    775
    0.07
    portion
    0.07
    неÑĢ
    0.07
    ÑĢина
    0.06
     Leban
    0.06
    eshire
    0.06
    atori
    0.06
    edList
    0.06
    ìĭ
    0.06
    &C
    0.06
    Activations Density 0.051%

    No Known Activations