© 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. 130099
    Prev
    Next
    INDEX
    Explanations

    texts that analyze themes and issues related to culture and 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
    hana
    -0.07
    eer
    -0.07
    radient
    -0.07
    ìŀij
    -0.06
    ecided
    -0.06
    еÑĢо
    -0.06
    ero
    -0.06
    eri
    -0.06
    wo
    -0.06
     âĹĦ
    -0.06
    POSITIVE LOGITS
     everything
    0.12
    :
    0.09
     various
    0.09
    everything
    0.08
     both
    0.08
     ranging
    0.08
    :↵
    0.07
     Everything
    0.07
    Everything
    0.07
    :*
    0.07
    Activations Density 0.286%

    No Known Activations