© 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. 88211
    Prev
    Next
    INDEX
    Explanations

    contact information and phone numbers in the text

    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
    olson
    -0.07
    ix
    -0.06
    ush
    -0.06
    icio
    -0.06
    ick
    -0.06
    /Foundation
    -0.06
    shot
    -0.06
     Consortium
    -0.06
    ay
    -0.05
    Č
    -0.05
    POSITIVE LOGITS
    INCLUDED
    0.08
    lien
    0.07
     Reign
    0.07
    uisse
    0.07
    ivos
    0.06
    ëŀij
    0.06
    BUY
    0.06
    æ´ĭ
    0.06
    ustom
    0.06
    vrier
    0.06
    Activations Density 0.008%

    No Known Activations