© 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. 89679
    Prev
    Next
    INDEX
    Explanations

    variations of the word "reveal" in different contexts

    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
    वर
    -0.08
    SizeMode
    -0.08
    ptype
    -0.07
    pis
    -0.07
    zimmer
    -0.07
    odian
    -0.07
    esel
    -0.07
    ropoda
    -0.07
    fried
    -0.07
    éĦ
    -0.07
    POSITIVE LOGITS
    croft
    0.08
    ries
    0.08
    ito
    0.07
    ry
    0.07
    ing
    0.07
     Revel
    0.07
    ution
    0.07
    ments
    0.07
    aries
    0.07
    aravel
    0.06
    Activations Density 0.005%

    No Known Activations