© 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. 22-LLAMASCOPE-RES-131K
    11. 3985
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and themes that reflect social issues and complexities in relationships

    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
     Dickinson
    -0.07
    alc
    -0.07
    r
    -0.06
     considerations
    -0.06
    оÑĢоÑĤ
    -0.06
    etime
    -0.06
    alf
    -0.06
    urs
    -0.06
    301
    -0.06
     for
    -0.06
    POSITIVE LOGITS
    endor
    0.07
    ecta
    0.07
    CAF
    0.07
    Intl
    0.07
     æ°
    0.07
    æ°ı
    0.07
    ìĸ´ê°Ģ
    0.07
    rens
    0.07
    illet
    0.07
    Viewport
    0.07
    Activations Density 0.035%

    No Known Activations