© 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. 18841
    Prev
    Next
    INDEX
    Explanations

    phrases involving the word "in" and its variations, often within the context of inclusion or presence

    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
    enberg
    -0.08
    ories
    -0.07
    asm
    -0.07
    vido
    -0.06
    uko
    -0.06
    lub
    -0.06
    oretical
    -0.06
     chy
    -0.06
    itele
    -0.06
    conde
    -0.06
    POSITIVE LOGITS
    ìŀIJìĿ¸
    0.07
    _IL
    0.07
    elden
    0.07
    onn
    0.07
    inally
    0.07
    estar
    0.06
    ãĢģãĢģ
    0.06
    pez
    0.06
    rag
    0.06
    (disposing
    0.06
    Activations Density 0.049%

    No Known Activations