© 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. 91868
    Prev
    Next
    INDEX
    Explanations

    phrases suggesting convenience and ease in making reservations or arrangements

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Opera
    -0.06
     æĻ®
    -0.06
    014
    -0.06
    iron
    -0.06
    ior
    -0.06
    ivec
    -0.05
    ance
    -0.05
     Demonstr
    -0.05
     trick
    -0.05
     resale
    -0.05
    POSITIVE LOGITS
    abox
    0.08
    enant
    0.07
    -step
    0.07
    holm
    0.07
    _hdl
    0.07
    zdy
    0.07
    ILLS
    0.07
    abad
    0.07
    _foreign
    0.07
    icaret
    0.07
    Activations Density 0.000%

    No Known Activations