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. 22-LLAMASCOPE-RES-131K
    6. 5547
    Prev
    Next
    INDEX
    Explanations

    mentions of the Avengers franchise and its associated films and characters

    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
    467
    -0.07
    azers
    -0.06
     Ign
    -0.06
    pto
    -0.06
    antar
    -0.06
    wel
    -0.06
    iana
    -0.06
    ertools
    -0.06
    gni
    -0.06
    .getStyle
    -0.06
    POSITIVE LOGITS
     Niet
    0.08
     Robbins
    0.07
     Evet
    0.07
     contrario
    0.06
     WARRANT
    0.06
    td
    0.06
    á»įn
    0.06
     Ul
    0.06
     Rahman
    0.06
    ouve
    0.06
    Activations Density 0.001%

    No Known Activations