© 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. 119091
    Prev
    Next
    INDEX
    Explanations

    references to notable architectural works and architects

    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
    åı¤
    -0.07
    ocket
    -0.07
    Advisor
    -0.06
    lfw
    -0.06
    avourites
    -0.06
    ç¹ģ
    -0.06
     fian
    -0.06
     Traditional
    -0.06
    "nil
    -0.06
    orque
    -0.06
    POSITIVE LOGITS
     design
    0.07
     designed
    0.07
     built
    0.07
    Designed
    0.07
     housing
    0.06
    built
    0.06
     Designed
    0.06
    arch
    0.06
     architecture
    0.06
     architects
    0.06
    Activations Density 0.015%

    No Known Activations