© 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. 91754
    Prev
    Next
    INDEX
    Explanations

    prominent political figures and their actions or statements

    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
    massage
    -0.07
    antha
    -0.07
    NullOr
    -0.07
    ลล
    -0.07
    osl
    -0.07
    .Release
    -0.07
    Enlarge
    -0.06
    athy
    -0.06
    Animating
    -0.06
    trail
    -0.06
    POSITIVE LOGITS
     ******************************************************************************↵
    0.07
     Appearance
    0.07
     visit
    0.07
     visits
    0.07
     visited
    0.06
    andal
    0.06
    .getHost
    0.06
    eral
    0.06
     beaut
    0.06
    ÑĥÑĩ
    0.06
    Activations Density 0.018%

    No Known Activations