© 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. 103860
    Prev
    Next
    INDEX
    Explanations

    expressions indicating comparisons or evaluations

    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
     Maver
    -0.07
    ses
    -0.07
    ÑĢÑıдÑĥ
    -0.07
    udu
    -0.07
    vest
    -0.06
    ç±į
    -0.06
    vens
    -0.06
    acie
    -0.06
    stderr
    -0.06
    verter
    -0.06
    POSITIVE LOGITS
    -available
    0.07
    imited
    0.07
     available
    0.07
     Given
    0.07
     Spell
    0.06
     dostup
    0.06
     approximation
    0.06
     possible
    0.06
     possibile
    0.06
     reasonably
    0.06
    Activations Density 0.016%

    No Known Activations