© 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. 28277
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Luis."

    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
    oust
    -0.09
    hausen
    -0.08
    ibu
    -0.08
    oud
    -0.08
    chia
    -0.07
    à¸Ľà¸£à¸°à¸¡
    -0.07
    imd
    -0.07
    âm
    -0.07
    maal
    -0.07
    oss
    -0.07
    POSITIVE LOGITS
    fully
    0.07
    opia
    0.07
    led
    0.06
    ing
    0.06
    riel
    0.06
    er
    0.06
    र
    0.06
    odus
    0.06
     Buckingham
    0.06
     de
    0.06
    Activations Density 0.002%

    No Known Activations