© 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. 118722
    Prev
    Next
    INDEX
    Explanations

    expressions indicating recommendations or suggestions to the reader

    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
    ourg
    -0.06
     Nicholson
    -0.06
     Prec
    -0.06
     behavior
    -0.06
    dale
    -0.06
     Flam
    -0.06
    idad
    -0.06
    phan
    -0.06
    iesz
    -0.06
     Fol
    -0.05
    POSITIVE LOGITS
     addCriterion
    0.08
    sein
    0.07
    ebo
    0.07
    lian
    0.07
    ellan
    0.07
    æĬµ
    0.07
    ало
    0.07
    .setdefault
    0.06
    LEAN
    0.06
    ди
    0.06
    Activations Density 0.002%

    No Known Activations