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. 11533
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people in a narrative context

    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
     Atatürk
    -0.08
    osg
    -0.07
    mpr
    -0.07
     Azerbai
    -0.07
    rary
    -0.06
    stance
    -0.06
    cox
    -0.06
    ãĥ©ãĤ¤ãĥ³
    -0.06
    WithContext
    -0.06
     indonesia
    -0.06
    POSITIVE LOGITS
     Hur
    0.12
     Cham
    0.11
     Montreal
    0.11
     Canadiens
    0.10
     fur
    0.10
     Quebec
    0.10
     Sie
    0.10
     Canada
    0.09
     Jes
    0.09
     Hoch
    0.09
    Activations Density 0.013%

    No Known Activations