© 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. 1185
    Prev
    Next
    INDEX
    Explanations

    elements related to weather and transportation

    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
     Fucked
    -0.08
    indow
    -0.07
    inee
    -0.07
    stery
    -0.06
    stk
    -0.06
    urope
    -0.06
     incom
    -0.06
    κη
    -0.06
    dux
    -0.06
    wner
    -0.06
    POSITIVE LOGITS
    acher
    0.06
    .rad
    0.06
    æį
    0.06
    iva
    0.06
    /npm
    0.06
    éĽ²
    0.06
    otte
    0.05
    kap
    0.05
    izm
    0.05
    اÙĤÙĦ
    0.05
    Activations Density 0.000%

    No Known Activations