© 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. 53774
    Prev
    Next
    INDEX
    Explanations

    phrases indicating probabilities or chances, particularly related to weather conditions

    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
     zdrav
    -0.08
    oeff
    -0.07
    agnostic
    -0.07
    enderit
    -0.07
    smarty
    -0.07
    rens
    -0.06
    .bz
    -0.06
    BUG
    -0.06
    imiter
    -0.06
    DBG
    -0.06
    POSITIVE LOGITS
     rain
    0.08
     precipitation
    0.07
    iji
    0.07
     showers
    0.07
     precip
    0.07
    achat
    0.07
     minor
    0.06
    minor
    0.06
     shower
    0.06
     vari
    0.06
    Activations Density 0.004%

    No Known Activations