© 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 EvalsExportsinterp-engineNEWAPI 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. 62420
    Prev
    Next
    INDEX
    Explanations

    temporal and contextual references 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
     Kidd
    -0.08
    éļİ
    -0.07
    letcher
    -0.06
     breath
    -0.06
    ders
    -0.06
     chiá»ģu
    -0.06
    eri
    -0.06
     lượt
    -0.06
    ewood
    -0.06
    Æ
    -0.06
    POSITIVE LOGITS
    /year
    0.10
    icals
    0.09
    nings
    0.08
     ago
    0.08
    -Year
    0.08
     çĭ
    0.08
    .year
    0.07
    (year
    0.07
    .Year
    0.07
    ning
    0.07
    Activations Density 0.034%

    No Known Activations