© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 128721
    Prev
    Next
    INDEX
    Explanations

    various forms and components of the word "ass."

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

    Tokens representing dictionary-style entries, especially terms that appear in reference works, Wikipedia pages, or other informational sources. These often contain proper nouns, technical terms, or words being defined within their respective contexts.

    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
    Äįet
    -0.08
    och
    -0.07
    avan
    -0.07
    Ø·Ùģ
    -0.07
    è¶Ĭ
    -0.06
    immer
    -0.06
    annya
    -0.06
     Armor
    -0.06
    itura
    -0.06
     daleko
    -0.06
    POSITIVE LOGITS
     meaning
    0.10
     Meaning
    0.09
     definition
    0.08
    noun
    0.08
    meaning
    0.08
    yonel
    0.07
     meanings
    0.07
     Definition
    0.07
    .Undef
    0.07
     pronounced
    0.07
    Activations Density 0.016%

    No Known Activations