© 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. 117225
    Prev
    Next
    INDEX
    Explanations

    references to the location Arkansas and its variations

    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
    rys
    -0.09
    eru
    -0.08
    ityEngine
    -0.07
     trá»ĭ
    -0.07
    izzard
    -0.07
    ÙĪغ
    -0.07
    jvu
    -0.07
    keit
    -0.07
    uchs
    -0.07
    ternet
    -0.07
    POSITIVE LOGITS
    ansas
    0.09
    loff
    0.08
    itecture
    0.08
    den
    0.07
    wright
    0.07
    oning
    0.07
     Bit
    0.06
    esian
    0.06
     Baldwin
    0.06
    asha
    0.06
    Activations Density 0.008%

    No Known Activations