© 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 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. 128924
    Prev
    Next
    INDEX
    Explanations

    variations of the word "proof."

    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
    ê»ĺ
    -0.08
    unch
    -0.07
    gi
    -0.07
    -gnu
    -0.07
    oral
    -0.07
    lle
    -0.07
    ughter
    -0.07
    iser
    -0.07
    alf
    -0.07
    vre
    -0.07
    POSITIVE LOGITS
    reading
    0.11
    lessly
    0.09
    reader
    0.07
    duc
    0.06
    íıIJ
    0.06
    -of
    0.06
    read
    0.06
    ing
    0.06
    ahn
    0.06
    /dis
    0.06
    Activations Density 0.015%

    No Known Activations