© 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. 88766
    Prev
    Next
    INDEX
    Explanations

    references to cold weather and freezing 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
    izzo
    -0.08
     Domestic
    -0.06
     based
    -0.05
     Skyl
    -0.05
    chema
    -0.05
    ites
    -0.05
    sei
    -0.05
    /
    -0.05
    .class
    -0.05
     IV
    -0.05
    POSITIVE LOGITS
    SCAN
    0.08
    cold
    0.08
    ÑĢаÐ
    0.08
    _OW
    0.07
    -blood
    0.07
    unnel
    0.07
    ;element
    0.07
    ERNEL
    0.07
    cctor
    0.07
     Affero
    0.07
    Activations Density 0.021%

    No Known Activations