© 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. 75546
    Prev
    Next
    INDEX
    Explanations

    words related to community and collective identity

    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
    æĹ
    -0.07
    abil
    -0.07
    earn
    -0.06
    anz
    -0.06
    .strategy
    -0.06
    ÑĨÑĸ
    -0.06
    än
    -0.06
    uzz
    -0.06
    446
    -0.06
    åģ´
    -0.06
    POSITIVE LOGITS
    rape
    0.07
    eon
    0.07
    ://%
    0.06
    icina
    0.06
    APSHOT
    0.06
    HttpException
    0.06
    camatan
    0.06
    ongyang
    0.06
    ÑĨин
    0.06
    ãĥ¼ãĥł
    0.06
    Activations Density 0.002%

    No Known Activations