© 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. 60029
    Prev
    Next
    INDEX
    Explanations

    aspects of historical biography and notable achievements

    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
    #__
    -0.08
    efs
    -0.07
    å²
    -0.07
    .nano
    -0.07
     oversh
    -0.07
    rats
    -0.07
     Profes
    -0.07
     <$
    -0.07
    gles
    -0.07
    виÑĩ
    -0.07
    POSITIVE LOGITS
     Weinstein
    0.07
    اذا
    0.06
    woord
    0.06
    loor
    0.06
    uron
    0.06
     briefly
    0.06
     reporters
    0.06
    och
    0.06
    -divider
    0.06
     various
    0.06
    Activations Density 0.043%

    No Known Activations