© 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. 82993
    Prev
    Next
    INDEX
    Explanations

    clothing sizes and labels

    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
     cul
    -0.07
    lessly
    -0.07
    ively
    -0.07
    ácil
    -0.07
    /live
    -0.07
     ÑĪп
    -0.06
    ings
    -0.06
     Ñģобой
    -0.06
    evi
    -0.06
    éné
    -0.06
    POSITIVE LOGITS
    -sized
    0.13
    -size
    0.12
     sized
    0.10
    -scale
    0.10
     size
    0.08
    size
    0.08
    =size
    0.07
     Sized
    0.07
     dimensions
    0.07
    以ä¸Ĭ
    0.07
    Activations Density 0.008%

    No Known Activations