© 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. 91571
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and expressions of personal requests or inquiries

    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
    ROKE
    -0.07
    ayas
    -0.07
    .synthetic
    -0.07
    lint
    -0.07
    -thumb
    -0.06
    inson
    -0.06
    .Elements
    -0.06
     bem
    -0.06
    clientId
    -0.06
    ạp
    -0.06
    POSITIVE LOGITS
    ân
    0.06
     please
    0.06
    278
    0.06
    TimeInterval
    0.06
    please
    0.06
    onna
    0.06
    occo
    0.05
     Penny
    0.05
    ister
    0.05
    £¼
    0.05
    Activations Density 0.006%

    No Known Activations