© 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. 70144
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate collaboration or unity

    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
     Scotia
    -0.07
     Pazar
    -0.07
    taj
    -0.07
    تÙĬÙĨ
    -0.07
     Franken
    -0.06
    drv
    -0.06
    emean
    -0.06
    ÑĥÑģк
    -0.06
    adx
    -0.06
    .spi
    -0.06
    POSITIVE LOGITS
    imentary
    0.07
    ½
    0.06
    erval
    0.06
    andez
    0.06
     ofType
    0.06
    iras
    0.06
    och
    0.05
    vé
    0.05
    ovel
    0.05
    wed
    0.05
    Activations Density 0.001%

    No Known Activations