© 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. 60361
    Prev
    Next
    INDEX
    Explanations

    decimal points or numbers that represent statistical data

    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
    jvu
    -0.06
    ulan
    -0.06
    phis
    -0.06
     bare
    -0.06
     Variant
    -0.06
    ucken
    -0.06
    ä¹
    -0.06
    aker
    -0.06
    peria
    -0.06
    ADER
    -0.06
    POSITIVE LOGITS
    AIN
    0.07
    ваÑı
    0.06
    zon
    0.06
    θα
    0.06
    صÙĦ
    0.06
    boom
    0.06
    ublik
    0.06
    elsif
    0.06
    _TIMES
    0.06
    uld
    0.06
    Activations Density 0.000%

    No Known Activations