© 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. 17-LLAMASCOPE-RES-131K
    11. 87933
    Prev
    Next
    INDEX
    Explanations

    references to training and behavior regulation of animals, particularly in contexts involving control and performance expectations

    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
     punches
    -0.07
    /perl
    -0.07
    anon
    -0.07
    dbg
    -0.07
     Punch
    -0.06
    anou
    -0.06
     punch
    -0.06
     punching
    -0.06
    UBLE
    -0.06
    tron
    -0.06
    POSITIVE LOGITS
    ortex
    0.07
    conto
    0.07
     fetch
    0.06
    åij½ä»¤
    0.06
    azzo
    0.06
     Shib
    0.06
    ISODE
    0.06
     Fetch
    0.06
    esture
    0.06
    iverse
    0.06
    Activations Density 0.002%

    No Known Activations