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. 11476
    Prev
    Next
    INDEX
    Explanations

    the name "McG" and its variations in the context of various documents

    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
    èį
    -0.08
     idi
    -0.07
    iculo
    -0.06
    zÅij
    -0.06
    ctors
    -0.06
    tml
    -0.06
    ÅĽnie
    -0.06
    638
    -0.06
    ież
    -0.06
    emailer
    -0.06
    POSITIVE LOGITS
    raw
    0.19
    overn
    0.18
    owan
    0.17
    hee
    0.16
    ee
    0.16
    inn
    0.14
    ibbon
    0.14
    arry
    0.14
    lash
    0.13
    wire
    0.13
    Activations Density 0.003%

    No Known Activations