© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 119356
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to weather conditions

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     my
    -0.06
     hol
    -0.06
    olit
    -0.06
     Sil
    -0.05
    olith
    -0.05
     Silence
    -0.05
    innitus
    -0.05
    åĨ¬
    -0.05
     Depths
    -0.05
     or
    -0.05
    POSITIVE LOGITS
     Ashe
    0.08
     venue
    0.08
    overn
    0.08
    erç
    0.07
    /vendors
    0.07
    Venue
    0.07
    unal
    0.07
     Venue
    0.07
    cheng
    0.07
    cpy
    0.07
    Activations Density 0.012%

    No Known Activations