© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 105921
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and 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
    ieri
    -0.07
    .descriptor
    -0.07
    halt
    -0.07
    orrow
    -0.07
    mund
    -0.07
    ç͍çļĦ
    -0.07
    Ĭ
    -0.06
     Levin
    -0.06
    ailer
    -0.06
    @qq
    -0.06
    POSITIVE LOGITS
     Rush
    0.07
     Annotation
    0.07
    ernet
    0.06
     panc
    0.06
    (jQuery
    0.06
    ÑĤив
    0.06
    ANNOT
    0.06
    Ñĥжд
    0.06
    IEWS
    0.06
    оÑĢом
    0.06
    Activations Density 0.021%

    No Known Activations