© 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. 2216
    Prev
    Next
    INDEX
    Explanations

    descriptors relating to weather conditions and their emotional impacts

    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
    inyin
    -0.06
    ctors
    -0.06
     numel
    -0.06
    ingen
    -0.06
    ertest
    -0.06
    911
    -0.06
    ationToken
    -0.06
     ÄĮeská
    -0.06
    unch
    -0.06
    ohana
    -0.06
    POSITIVE LOGITS
     type
    0.09
     kind
    0.08
    éĤ£ç§į
    0.08
    type
    0.08
    ä¸Ģç§į
    0.08
     sort
    0.08
    ç±»åŀĭ
    0.07
     kinds
    0.07
     strand
    0.07
    "type
    0.07
    Activations Density 0.068%

    No Known Activations