© 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. 107432
    Prev
    Next
    INDEX
    Explanations

    technical terms and parameters related to configuration and connections in a programming context

    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
     Oswald
    -0.07
    gren
    -0.06
    902
    -0.06
    UBL
    -0.06
    akedown
    -0.06
     div
    -0.06
    æ¼
    -0.06
    mith
    -0.06
     podium
    -0.06
    iva
    -0.06
    POSITIVE LOGITS
    екаÑĢ
    0.09
    roker
    0.08
    çĵľ
    0.07
     dialect
    0.07
    æ±Ĺ
    0.07
    dia
    0.07
    :host
    0.07
     dia
    0.06
    áng
    0.06
     ÑħÑĥд
    0.06
    Activations Density 0.001%

    No Known Activations