© 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. 84900
    Prev
    Next
    INDEX
    Explanations

    references to adults and adult-related contexts

    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
    etta
    -0.08
     buá»Ļc
    -0.07
    /screen
    -0.07
    Å¡ti
    -0.07
    gaard
    -0.07
    gli
    -0.07
    indeki
    -0.07
    uesta
    -0.07
    à¤ģ
    -0.07
    feit
    -0.07
    POSITIVE LOGITS
    -child
    0.10
    thood
    0.10
    -only
    0.07
    preneur
    0.07
    575
    0.07
     who
    0.07
    rosse
    0.07
    esc
    0.07
    /y
    0.07
    ä¿Ĺ
    0.06
    Activations Density 0.010%

    No Known Activations