© 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. 17-LLAMASCOPE-RES-131K
    11. 74507
    Prev
    Next
    INDEX
    Explanations

    expressions of sales and promotional content

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

    Structural elements that indicate transitions between content sections, often including punctuation marks, navigation links, or formatting artifacts from web content.

    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
     Genre
    -0.07
    (PR
    -0.07
    ocos
    -0.07
    Äįan
    -0.07
    ocrates
    -0.07
    culus
    -0.06
    elow
    -0.06
    undance
    -0.06
    oller
    -0.06
    coop
    -0.06
    POSITIVE LOGITS
     science
    0.08
     Science
    0.07
    aje
    0.07
    history
    0.07
     Ear
    0.06
     Py
    0.06
     fascinating
    0.06
    Science
    0.06
     history
    0.06
     historians
    0.06
    Activations Density 0.036%

    No Known Activations