© 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 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. 88519
    Prev
    Next
    INDEX
    Explanations

    references to historical places and their significance

    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
     ctxt
    -0.06
    arendra
    -0.06
    amo
    -0.06
    addock
    -0.06
    hurst
    -0.06
    uan
    -0.06
     involved
    -0.06
    arcy
    -0.06
    amarin
    -0.06
    cest
    -0.06
    POSITIVE LOGITS
    lio
    0.07
    AMIL
    0.07
    alc
    0.07
    olith
    0.07
    oft
    0.07
    ,ep
    0.07
    yne
    0.07
    á»ĵn
    0.07
    mers
    0.06
    utherland
    0.06
    Activations Density 0.014%

    No Known Activations