© 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. 9-LLAMASCOPE-RES-131K
    11. 96271
    Prev
    Next
    INDEX
    Explanations

    indefinite and definite articles

    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
    utex
    -0.08
    iese
    -0.07
    ivant
    -0.07
    ustos
    -0.06
    urb
    -0.06
    ãĥ¼ãĤ¹
    -0.06
     UIScreen
    -0.06
    eza
    -0.06
    ampp
    -0.06
    erdale
    -0.06
    POSITIVE LOGITS
    andre
    0.07
    άζ
    0.06
    ÑĤик
    0.06
    ylko
    0.06
    861
    0.06
    stride
    0.06
    arend
    0.06
     ÑģÑĤало
    0.06
     vacant
    0.06
    942
    0.06
    Activations Density 0.017%

    No Known Activations