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. 44298
    Prev
    Next
    INDEX
    Explanations

    specific characters and symbols often used in written language

    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
     neighbouring
    -0.07
     neighbourhood
    -0.07
     aluminium
    -0.06
     Organisation
    -0.06
     Defence
    -0.06
     neighbours
    -0.06
     jewellery
    -0.06
    organisation
    -0.06
    amics
    -0.06
     neighbour
    -0.06
    POSITIVE LOGITS
     $
    0.08
     wagon
    0.08
     price
    0.08
     prices
    0.08
     .$
    0.07
     email
    0.07
     pricing
    0.07
     priced
    0.07
     Specify
    0.07
    Specify
    0.07
    Activations Density 0.006%

    No Known Activations