© 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. 55503
    Prev
    Next
    INDEX
    Explanations

    references to directors and authors in various contexts

    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
    woo
    -0.07
    .getChildAt
    -0.07
    UFFIX
    -0.06
     Dort
    -0.06
    =yes
    -0.06
    rer
    -0.06
    woke
    -0.06
    pects
    -0.06
    .asInstanceOf
    -0.06
    pective
    -0.06
    POSITIVE LOGITS
    (s
    0.07
    fragistics
    0.07
     اÙĦØ¢
    0.07
    icens
    0.06
    kup
    0.06
    uzzi
    0.06
    attle
    0.06
    ovna
    0.06
    ä
    0.06
    airs
    0.06
    Activations Density 0.003%

    No Known Activations