© 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. 89844
    Prev
    Next
    INDEX
    Explanations

    phrases related to attending events or performances

    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
    ovel
    -0.09
    xes
    -0.09
    جر
    -0.08
    udas
    -0.07
    itters
    -0.07
    dney
    -0.07
    issen
    -0.07
    à¥įवय
    -0.07
    /buttons
    -0.07
    chet
    -0.06
    POSITIVE LOGITS
    lah
    0.07
     lectures
    0.07
    /view
    0.07
    /part
    0.06
    ants
    0.06
    ees
    0.06
    ship
    0.06
    gether
    0.06
    (ed
    0.06
    431
    0.06
    Activations Density 0.012%

    No Known Activations