© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 44459
    Prev
    Next
    INDEX
    Explanations

    local communities and groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     policymakers
    -0.10
    人æīį
    -0.10
     tack
    -0.09
     insiders
    -0.09
     conspir
    -0.09
     Marine
    -0.09
    983
    -0.09
    oyo
    -0.08
     ministries
    -0.08
     innoc
    -0.08
    POSITIVE LOGITS
     groups
    0.22
     associations
    0.19
     unions
    0.18
     representative
    0.18
    groups
    0.18
     Groups
    0.18
     union
    0.17
     representatives
    0.17
     local
    0.16
    Groups
    0.16
    Activations Density 0.067%

    No Known Activations