© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 74670
    Prev
    Next
    INDEX
    Explanations

    keywords related to provider registration and policies in a technical or programming context

    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
    ersonic
    -0.07
     пÑĢоз
    -0.07
     factorial
    -0.06
    ONGL
    -0.06
    æŁ»
    -0.06
    <!--[
    -0.06
     nackte
    -0.06
     Henderson
    -0.06
     Zahl
    -0.06
    AREST
    -0.06
    POSITIVE LOGITS
    California
    0.07
    ante
    0.07
     california
    0.06
    AGO
    0.06
    eshire
    0.06
     California
    0.06
    #!
    0.06
    oot
    0.06
     mojo
    0.06
     Serie
    0.06
    Activations Density 0.000%

    No Known Activations