© 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. 31711
    Prev
    Next
    INDEX
    Explanations

    instances of the word "are" and associated phrases that indicate listings or descriptions

    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
    еÑĢÑĪ
    -0.07
     Chancellor
    -0.07
     Gle
    -0.06
    led
    -0.06
    RIES
    -0.06
    otos
    -0.06
    esc
    -0.06
    amientos
    -0.06
    -chief
    -0.06
    å¼ķãģį
    -0.06
    POSITIVE LOGITS
    ffa
    0.07
    andon
    0.06
    AccessException
    0.06
     brand
    0.06
    ethyst
    0.06
     hang
    0.06
     infl
    0.06
    akte
    0.06
    ingham
    0.06
     Abe
    0.06
    Activations Density 0.001%

    No Known Activations