© 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. 63134
    Prev
    Next
    INDEX
    Explanations

    phrases related to fundraising and charitable events

    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
    ayan
    -0.08
    elian
    -0.06
    regor
    -0.06
    пÑĢ
    -0.06
     Shel
    -0.06
    mant
    -0.05
    _COMP
    -0.05
    stoff
    -0.05
    SystemService
    -0.05
    gue
    -0.05
    POSITIVE LOGITS
    _unregister
    0.07
     teams
    0.07
     Assigned
    0.06
    longleftrightarrow
    0.06
    ìĥ
    0.06
    lea
    0.06
    ç²Ĵ
    0.06
    acer
    0.06
    assigned
    0.06
    ReadOnly
    0.06
    Activations Density 0.006%

    No Known Activations