© 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. 15-LLAMASCOPE-RES-131K
    11. 86735
    Prev
    Next
    INDEX
    Explanations

    references to cinematic works or adaptations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Section headers for reference sections (like "External links", "Bibliography", "References") that appear at the end of documents in various languages, typically followed by lists of citations or links.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    ÑĢÑĥб
    -0.08
    IRROR
    -0.06
    ibling
    -0.06
     Armour
    -0.06
    iner
    -0.06
    cházÃŃ
    -0.06
    /movie
    -0.06
    thr
    -0.06
    Fa
    -0.06
    erie
    -0.05
    POSITIVE LOGITS
    ory
    0.11
    ing
    0.10
    usz
    0.09
    imitive
    0.08
    enticate
    0.08
    Į¨
    0.08
    ING
    0.08
    oload
    0.07
    bsite
    0.07
    äºİ
    0.07
    Activations Density 0.011%

    No Known Activations