© 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. 69151
    Prev
    Next
    INDEX
    Explanations

    aspects related to community and social interactions in specific locations

    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
    æ·»
    -0.07
     PropertyInfo
    -0.07
    aise
    -0.07
    ilig
    -0.06
     sher
    -0.06
    ç±
    -0.06
     everywhere
    -0.06
     conexion
    -0.06
    umatic
    -0.06
    sher
    -0.06
    POSITIVE LOGITS
     locals
    0.09
    locals
    0.08
     LOCAL
    0.07
     local
    0.06
     lokal
    0.06
     nearby
    0.06
     frequent
    0.06
    éĻĦè¿ij
    0.06
    (local
    0.06
     gent
    0.06
    Activations Density 0.022%

    No Known Activations