© 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. 82298
    Prev
    Next
    INDEX
    Explanations

    positive expressions about summer camp experiences and activities

    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
    ~
    -0.08
    ,
    -0.08
     -
    -0.07
    :
    -0.07
     beg
    -0.06
    olon
    -0.06
     round
    -0.06
    aben
    -0.06
     grou
    -0.06
    !
    -0.06
    POSITIVE LOGITS
     nues
    0.09
    ALAR
    0.08
     cuckold
    0.08
    ÐĿаÑģ
    0.08
    ÑĤап
    0.08
    ----------</
    0.08
    éĿ©
    0.07
     ÑģвеÑĢ
    0.07
    é§
    0.07
     creo
    0.07
    Activations Density 0.018%

    No Known Activations