Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43426
    Prev
    Next
    INDEX
    Explanations

    numerical data and ticket information related to 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
    áct
    -0.07
    dum
    -0.07
     strokeLine
    -0.06
     forState
    -0.06
    λÏī
    -0.06
    ÑĢаÑģÑĤа
    -0.06
    alem
    -0.06
    Stores
    -0.06
     Stores
    -0.06
     jenter
    -0.06
    POSITIVE LOGITS
     rows
    0.13
     Rows
    0.13
     sections
    0.12
     balcony
    0.12
     section
    0.12
     aisle
    0.12
     seats
    0.11
     row
    0.11
     Section
    0.11
     Row
    0.11
    Activations Density 0.016%

    No Known Activations