Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 40457
    Prev
    Next
    INDEX
    Explanations

    statistical measures and mathematical functions related to graphs

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

    Punctuation and special characters (commas, parentheses) or technical tokens that appear in formal contexts such as mathematical notation, programming code, or structured text.

    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
     â
    -0.08
    елен
    -0.07
    )(*
    -0.07
    .'<
    -0.07
     ÃĶ
    -0.07
    鹿
    -0.07
     recep
    -0.07
    olute
    -0.07
     withd
    -0.07
     Ãİ
    -0.07
    POSITIVE LOGITS
    .scalablytyped
    0.07
    @nate
    0.06
     [
    0.06
    719
    0.06
     jugg
    0.06
     &
    0.06
    ysi
    0.06
       
    0.06
     Rosenberg
    0.06
     
    0.05
    Activations Density 0.293%

    No Known Activations