© 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. 85903
    Prev
    Next
    INDEX
    Explanations

    conditional statements and phrases indicating potential or possibility

    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
    luž
    -0.06
    ãĤ¥
    -0.06
    à¤¾à¤Ł
    -0.06
    unik
    -0.06
    riel
    -0.06
     Bra
    -0.06
     rarely
    -0.06
     hopefully
    -0.05
    .extension
    -0.05
    زÙĨ
    -0.05
    POSITIVE LOGITS
     tempted
    0.11
     tempting
    0.10
     temptation
    0.09
     Tem
    0.09
    mere
    0.08
    ãĥ¼ãĥį
    0.08
    tempt
    0.07
     could
    0.07
     tem
    0.07
     fácil
    0.07
    Activations Density 0.022%

    No Known Activations