© 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. 40670
    Prev
    Next
    INDEX
    Explanations

    references to logistical and technical aspects of processes or events

    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
    ongan
    -0.08
    íį¼
    -0.07
    esModule
    -0.07
    /company
    -0.07
    ský
    -0.07
    atel
    -0.06
    Ä°Y
    -0.06
    /octet
    -0.06
    JECTED
    -0.06
    enco
    -0.06
    POSITIVE LOGITS
     aspects
    0.10
     Aspect
    0.10
    ament
    0.10
     aspect
    0.08
    istical
    0.08
    æĸ¹éĿ¢
    0.08
    Aspect
    0.08
     matters
    0.07
    istol
    0.07
    /admin
    0.07
    Activations Density 0.026%

    No Known Activations