© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 26749
    Prev
    Next
    INDEX
    Explanations

    references to economic performance and analysis

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

    Words and phrases that bridge between sentences or connect ideas within paragraphs, often including verbs, conjunctions, and descriptive elements that maintain narrative flow in informational or analytical 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
     Rope
    -0.07
    ictim
    -0.06
    thood
    -0.06
    outu
    -0.06
    tier
    -0.06
    ãĥ¼ãĥĨãĤ£
    -0.06
    ections
    -0.06
     dazz
    -0.06
    otti
    -0.06
    eur
    -0.05
    POSITIVE LOGITS
    ëĭĿ
    0.08
    §è¡Į
    0.07
     values
    0.07
    CLOSE
    0.07
    .average
    0.07
     average
    0.07
    åĢ¤
    0.07
    .gdx
    0.07
    VALUES
    0.07
    \FrameworkBundle
    0.07
    Activations Density 0.064%

    No Known Activations