© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 62180
    Prev
    Next
    INDEX
    Explanations

    references to news, articles, publications, and social media related content

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

    Website navigation elements or section links (like "News", "Programs", "Staff", "Events", "Archives") that represent different content categories on organizational websites.

    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
    -preview
    -0.06
     Aub
    -0.06
    ing
    -0.06
     previews
    -0.06
    .uni
    -0.05
     Preview
    -0.05
    HING
    -0.05
    ноÑģÑı
    -0.05
    .rb
    -0.05
    internet
    -0.05
    POSITIVE LOGITS
    abox
    0.07
    ATEGORIES
    0.07
    ormsg
    0.07
     ComVisible
    0.07
    θη
    0.07
    PropTypes
    0.07
     BusinessException
    0.07
    itm
    0.07
    awan
    0.07
    .xlsx
    0.07
    Activations Density 0.036%

    No Known Activations