© 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. 53735
    Prev
    Next
    INDEX
    Explanations

    phrases indicating existence or affirmation

    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
     Sanayi
    -0.07
     воÑĢ
    -0.07
    hei
    -0.07
    OSC
    -0.07
     vaz
    -0.07
    ibold
    -0.07
    ACY
    -0.06
    reator
    -0.06
    consistent
    -0.06
    (Str
    -0.06
    POSITIVE LOGITS
    rica
    0.06
    abi
    0.06
    andle
    0.06
    metis
    0.06
    kee
    0.06
    reward
    0.05
    788
    0.05
     Lynn
    0.05
    NECT
    0.05
    fos
    0.05
    Activations Density 0.001%

    No Known Activations