© 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. 15-LLAMASCOPE-RES-131K
    6. 346
    Prev
    Next
    INDEX
    Explanations

    keywords or terms associated with gaming and technology contexts

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

    Single-word tokens that commonly appear as part of website navigation, search results, or product listings. They typically represent descriptive keywords or classification terms that might be used in URLs, tags, or database categorization.

    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
    isor
    -0.07
    icity
    -0.06
    anch
    -0.06
    ÑĢиз
    -0.06
    isy
    -0.06
    angler
    -0.06
    rise
    -0.06
    angle
    -0.06
    irie
    -0.06
    oš
    -0.06
    POSITIVE LOGITS
    bfd
    0.07
    printStats
    0.07
    ä»ĭ
    0.06
    subclass
    0.06
    erten
    0.06
    леÑĢг
    0.06
    OfYear
    0.06
    è¼ī
    0.06
    GetValue
    0.06
     cle
    0.06
    Activations Density 0.001%

    No Known Activations