© 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. 625
    Prev
    Next
    INDEX
    Explanations

    references to numerical data and statistics

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

    Structural punctuation or syntax elements that connect or separate parts of text, appearing at clause boundaries, between code blocks, or in mathematical expressions.

    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
    пов
    -0.07
    ied
    -0.06
    uhe
    -0.06
    eyim
    -0.06
    PerPixel
    -0.06
    ãĥ³ãĤ¯
    -0.06
    hea
    -0.06
    umbo
    -0.06
    दम
    -0.06
    梯
    -0.06
    POSITIVE LOGITS
    odo
    0.07
    lik
    0.06
    other
    0.06
    itto
    0.06
    ãģĿãģ®ä»ĸ
    0.06
    Lik
    0.06
    handling
    0.06
     likewise
    0.06
    inson
    0.06
     andere
    0.06
    Activations Density 0.180%

    No Known Activations