© 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. 89475
    Prev
    Next
    INDEX
    Explanations

    punctuations and conjunctions indicating connectivity within the text

    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
    azu
    -0.08
    encil
    -0.07
    zyst
    -0.07
     åł
    -0.07
     Clo
    -0.06
     tetas
    -0.06
     whereas
    -0.06
    reeNode
    -0.06
     Conce
    -0.06
    hon
    -0.06
    POSITIVE LOGITS
    lett
    0.06
    Ñİк
    0.06
    amy
    0.06
    rens
    0.06
    .Tables
    0.06
    anic
    0.06
     ÑĦаÑĢ
    0.06
    íĻľ
    0.06
    á»įt
    0.06
    iker
    0.06
    Activations Density 0.002%

    No Known Activations