© 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. 86916
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and references within text

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

    Lines that begin with "A:" or just "A" at the start of a paragraph, marking them as answers in a Q&A format. These answer segments usually provide explanations, solutions, or clarifications to preceding questions.

    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
     York
    -0.06
    oph
    -0.06
    vang
    -0.06
     mole
    -0.06
    il
    -0.06
    ase
    -0.06
    affe
    -0.05
    виг
    -0.05
    çļĦäºĭ
    -0.05
    .loaded
    -0.05
    POSITIVE LOGITS
    uitka
    0.08
    _TAC
    0.08
    isci
    0.07
    æĹıèĩªæ²»
    0.07
    -columns
    0.07
    èĵ
    0.07
    ê¸ī
    0.07
    ød
    0.07
    ableViewController
    0.07
    istrovstvÃŃ
    0.07
    Activations Density 0.004%

    No Known Activations