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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 83801
    Prev
    Next
    INDEX
    Explanations

    structured phrases and terminology related to product specifications

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

    Text fragments that appear immediately before punctuation marks or after section transitions. These often include partial phrases, conjunctions, or prepositions at the start or end of content sections, particularly in website or document formatting where content breaks occur.

    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
    etu
    -0.07
    angu
    -0.07
    enties
    -0.07
    à¥įपन
    -0.06
     prostitut
    -0.06
    ears
    -0.06
    linger
    -0.06
     parten
    -0.06
    emme
    -0.06
    .dsl
    -0.06
    POSITIVE LOGITS
    ckill
    0.06
    illard
    0.06
    âĢı
    0.06
    (equalTo
    0.06
    \Eloquent
    0.06
    qrst
    0.06
     van
    0.06
    errat
    0.05
     Id
    0.05
     etc
    0.05
    Activations Density 0.517%

    No Known Activations