© 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 EvalsExportsinterp-engineNEWAPI 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. 81878
    Prev
    Next
    INDEX
    Explanations

    weather-related discussions and comparisons

    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
    oger
    -0.07
    .extract
    -0.06
    δη
    -0.06
    thresh
    -0.06
    oud
    -0.05
    Wunused
    -0.05
    åı¤
    -0.05
    threshold
    -0.05
    Ļ
    -0.05
     unknown
    -0.05
    POSITIVE LOGITS
     temperature
    0.07
    idity
    0.07
    oft
    0.07
     temperatures
    0.07
    humidity
    0.07
     ÑģмеÑĢ
    0.07
     rarely
    0.07
    åģ¶
    0.07
    temperature
    0.06
     nationals
    0.06
    Activations Density 0.010%

    No Known Activations