© 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. 17-LLAMASCOPE-RES-131K
    11. 125978
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components in web development

    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
    ếp
    -0.09
    zcze
    -0.09
    antan
    -0.08
    coli
    -0.08
    ovali
    -0.08
    iyah
    -0.08
    ocity
    -0.08
    vyk
    -0.08
    ibir
    -0.08
    colo
    -0.08
    POSITIVE LOGITS
     Stewart
    0.05
    st
    0.05
    ared
    0.05
     Loved
    0.05
    ARED
    0.05
     Ú©Ùħ
    0.05
    thur
    0.05
    SF
    0.05
     Christoph
    0.05
    cam
    0.05
    Activations Density 0.001%

    No Known Activations