© 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. 76639
    Prev
    Next
    INDEX
    Explanations

    years of birth or significant dates

    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
     Hutchinson
    -0.07
    å¥ı
    -0.06
    308
    -0.06
    ÑĪев
    -0.06
    ï¼ł
    -0.06
     Mish
    -0.06
     Åŀehir
    -0.06
    icl
    -0.06
    ogo
    -0.06
    orta
    -0.06
    POSITIVE LOGITS
    SError
    0.08
    rient
    0.07
    rip
    0.07
    aves
    0.06
    Ñij
    0.06
    stal
    0.06
    rych
    0.06
    uns
    0.06
    -era
    0.06
    ÛĮات
    0.06
    Activations Density 0.001%

    No Known Activations