© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 108620
    Prev
    Next
    INDEX
    Explanations

    variations of the word "dul" or "dull," likely indicating a focus on aspects related to dullness or monotony

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    iale
    -0.08
    esel
    -0.06
    oyo
    -0.06
    istol
    -0.06
    kud
    -0.06
    ToBounds
    -0.06
    hread
    -0.06
    istros
    -0.06
    .Assembly
    -0.06
     ho
    -0.06
    POSITIVE LOGITS
    lex
    0.07
    quer
    0.07
    ervo
    0.07
    bert
    0.07
    aml
    0.06
    iyet
    0.06
    dup
    0.06
     Nich
    0.06
    authors
    0.06
    led
    0.06
    Activations Density 0.002%

    No Known Activations