© 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. 41162
    Prev
    Next
    INDEX
    Explanations

    numerical values and references to legal citations

    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
    ald
    -0.06
    bris
    -0.06
    orest
    -0.06
    ä¸ģ
    -0.06
    abad
    -0.06
    entin
    -0.06
    StringBuilder
    -0.06
    æĹ
    -0.06
     Xxx
    -0.06
    /inet
    -0.06
    POSITIVE LOGITS
     Guardian
    0.07
    Guard
    0.06
    109
    0.06
    vig
    0.06
    लत
    0.06
    AGIC
    0.06
    ÑĢд
    0.06
    ITES
    0.05
     ob
    0.05
    Void
    0.05
    Activations Density 0.010%

    No Known Activations