© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 39925
    Prev
    Next
    INDEX
    Explanations

    features related to shoe and clothing design

    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
    æŀ¶
    -0.07
    ire
    -0.06
    wire
    -0.06
    pike
    -0.06
    crm
    -0.06
    aidu
    -0.06
    addons
    -0.06
    .ax
    -0.06
    agger
    -0.06
    mis
    -0.06
    POSITIVE LOGITS
    ienne
    0.07
    istrovstvÃŃ
    0.07
    esz
    0.07
    ẽ
    0.06
     запаÑģ
    0.06
     Abyss
    0.06
    jong
    0.06
    ãĢ
    0.06
    à¤¿à¤Ľà¤²
    0.06
     âĸ³
    0.06
    Activations Density 0.004%

    No Known Activations