© 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. 118592
    Prev
    Next
    INDEX
    Explanations

    references to services, particularly in the context of technology and career development

    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
    (es
    -0.07
    æ´¾
    -0.07
    askets
    -0.07
    жа
    -0.07
    .Foundation
    -0.06
    Hang
    -0.06
    PÅĻÃŃ
    -0.06
    éĻµ
    -0.06
    hiba
    -0.06
     McGr
    -0.06
    POSITIVE LOGITS
     division
    0.08
     Division
    0.08
    artment
    0.08
     department
    0.07
     office
    0.07
     Circular
    0.07
     staff
    0.07
    anza
    0.06
    637
    0.06
    division
    0.06
    Activations Density 0.046%

    No Known Activations