© 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. 78938
    Prev
    Next
    INDEX
    Explanations

    expressions of obligation or necessity

    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
    iso
    -0.07
    ollo
    -0.07
    вий
    -0.07
    ago
    -0.06
    cce
    -0.06
    èĤ²
    -0.06
    odus
    -0.06
    æģµ
    -0.06
     деÑĢжавного
    -0.06
     CES
    -0.06
    POSITIVE LOGITS
    utorial
    0.07
    oyer
    0.07
    ammed
    0.06
    ftar
    0.06
     Shorts
    0.06
    ETO
    0.06
    nit
    0.06
    ãĤ·ãĤ¢
    0.06
    gate
    0.06
    ÑĢоÑĤ
    0.06
    Activations Density 0.008%

    No Known Activations