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

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 89071
    Prev
    Next
    INDEX
    Explanations

    phrases related to outdoor recreational activities, particularly fishing and biking

    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
    sworth
    -0.07
    ãĥ¥ãĥ¼
    -0.07
     putas
    -0.07
    Touches
    -0.06
    ências
    -0.06
    /topics
    -0.06
    ceae
    -0.06
    arnation
    -0.06
     tamp
    -0.06
    ádu
    -0.06
    POSITIVE LOGITS
     beginners
    0.07
     beginner
    0.07
    _here
    0.07
    autoload
    0.06
     here
    0.06
    here
    0.06
    588
    0.06
     formations
    0.06
     Beginners
    0.06
    ì§ĢìļĶ
    0.06
    Activations Density 0.029%

    No Known Activations