© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 42691
    Prev
    Next
    INDEX
    Explanations

    instances of the word "palpable" and its variations, indicating a focus on strong emotional or physical sensations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    'gc
    -0.08
    Ư
    -0.07
    elves
    -0.07
     patron
    -0.07
    edition
    -0.07
    ture
    -0.06
    ekil
    -0.06
    PageIndex
    -0.06
    essen
    -0.06
    _hor
    -0.06
    POSITIVE LOGITS
    igned
    0.08
    resco
    0.07
    yna
    0.06
    غة
    0.06
    ضة
    0.06
    ily
    0.06
    urg
    0.06
    onso
    0.06
    aroo
    0.06
    cid
    0.06
    Activations Density 0.002%

    No Known Activations