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. 44093
    Prev
    Next
    INDEX
    Explanations

    specific names and identifiers related to brands or products

    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
     Canadian
    -0.08
     canadian
    -0.08
    Canadian
    -0.07
     Canada
    -0.07
     canada
    -0.07
    Toronto
    -0.07
     Toronto
    -0.07
    Canada
    -0.07
    ç¦ģ
    -0.06
     Canadians
    -0.06
    POSITIVE LOGITS
     family
    0.11
     Family
    0.10
     clinic
    0.10
     GP
    0.10
     clinics
    0.10
     Primary
    0.10
    .family
    0.09
     GAP
    0.09
     FAMILY
    0.09
     island
    0.09
    Activations Density 0.003%

    No Known Activations