© 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. 62018
    Prev
    Next
    INDEX
    Explanations

    references to specific details and inquiries for clarification

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

    Phrases that provide specific descriptive details about previously mentioned subjects, often containing connecting prepositions like "of," "about," or "what" that link general concepts to their specific attributes.

    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
     Schl
    -0.07
    spb
    -0.06
    olah
    -0.06
    å´İ
    -0.06
    onium
    -0.06
    choice
    -0.06
    tere
    -0.06
    eprom
    -0.06
    à¤ł
    -0.06
     domic
    -0.06
    POSITIVE LOGITS
    apus
    0.07
    hower
    0.07
     whatever
    0.07
    aju
    0.07
     ấy
    0.07
    à¥Īà¤Ĺ
    0.07
    对æĸ¹
    0.07
    .problem
    0.07
    izon
    0.06
    fleet
    0.06
    Activations Density 0.123%

    No Known Activations