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. 5583
    Prev
    Next
    INDEX
    Explanations

    terms related to family relationships and connections

    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
    asil
    -0.08
    inan
    -0.08
    ummings
    -0.08
    amedi
    -0.07
    anko
    -0.07
    obic
    -0.07
    /display
    -0.07
    asio
    -0.07
    ling
    -0.07
    tail
    -0.07
    POSITIVE LOGITS
     who
    0.11
    hood
    0.11
     whom
    0.11
     members
    0.08
    /close
    0.08
    age
    0.08
    /f
    0.07
    kin
    0.07
    /business
    0.07
    ately
    0.06
    Activations Density 0.011%

    No Known Activations