© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 62797
    Prev
    Next
    INDEX
    Explanations

    non-word characters and symbols, particularly slashes

    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
    o
    -0.07
    ath
    -0.06
    biz
    -0.06
    bay
    -0.06
    .identity
    -0.06
    hum
    -0.06
     uç
    -0.05
    /http
    -0.05
     equival
    -0.05
    Æ¡n
    -0.05
    POSITIVE LOGITS
    aterangepicker
    0.07
    íĶĪ
    0.07
    PRETTY
    0.07
    engin
    0.07
    amiliar
    0.06
    sled
    0.06
    cntl
    0.06
    ensch
    0.06
    dana
    0.06
    UTTON
    0.06
    Activations Density 0.003%

    No Known Activations