© 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. 116904
    Prev
    Next
    INDEX
    Explanations

    numerical values and their associated units of measurement

    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
    она
    -0.06
    }->
    -0.06
    ÅĻÃŃd
    -0.06
    finity
    -0.06
    ocks
    -0.06
    illion
    -0.06
    ием
    -0.06
    VEST
    -0.06
    pendicular
    -0.06
    ould
    -0.06
    POSITIVE LOGITS
     USA
    0.09
    USA
    0.08
    usa
    0.08
     America
    0.07
     usa
    0.07
     Americans
    0.07
     СШÐIJ
    0.07
    piar
    0.07
    ç¾İåĽ½
    0.07
     US
    0.06
    Activations Density 0.007%

    No Known Activations