© 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. 5096
    Prev
    Next
    INDEX
    Explanations

    titles or headings of sections in a document

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

    Section headers or titles that introduce new content entries in directory-style listings, often followed by details about locations, products, or services.

    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
    ¸ı
    -0.07
    chter
    -0.07
    вай
    -0.07
    cpf
    -0.07
     Cald
    -0.06
    Inspectable
    -0.06
    ÙĨØ´
    -0.06
    htdocs
    -0.06
    ator
    -0.06
    erokee
    -0.06
    POSITIVE LOGITS
     another
    0.09
    another
    0.08
     Another
    0.07
    ↵↵
    0.07
    jours
    0.06
    alla
    0.06
    Another
    0.06
    0.06
    egin
    0.06
    ache
    0.06
    Activations Density 0.011%

    No Known Activations