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. 43629
    Prev
    Next
    INDEX
    Explanations

    references to taxation and tax-related issues

    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
    ustos
    -0.08
    emoc
    -0.07
     bacheca
    -0.07
    anco
    -0.07
    ilibrium
    -0.06
    aleb
    -0.06
    braco
    -0.06
     activeClassName
    -0.06
    fork
    -0.06
    roke
    -0.06
    POSITIVE LOGITS
     avoidance
    0.13
     evasion
    0.11
     aggressive
    0.11
     ev
    0.10
     Avoid
    0.10
     offshore
    0.10
     shelters
    0.09
     schemes
    0.09
     avoid
    0.09
    avoid
    0.09
    Activations Density 0.011%

    No Known Activations