© 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. 80373
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software settings and configurations

    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
     Deck
    -0.07
    .compat
    -0.07
    ObjectContext
    -0.07
     доÑģÑĤ
    -0.07
    -addons
    -0.07
    ŀĭ
    -0.07
    Deck
    -0.07
    orney
    -0.07
    xcb
    -0.06
    !=(
    -0.06
    POSITIVE LOGITS
     togg
    0.09
     toggle
    0.09
     active
    0.08
     OFF
    0.08
    toggle
    0.08
     setting
    0.07
    .enabled
    0.07
     turned
    0.07
    Toggle
    0.07
     enabled
    0.07
    Activations Density 0.025%

    No Known Activations