© 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. 38683
    Prev
    Next
    INDEX
    Explanations

    endangered or threatened status

    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
    erty
    -0.10
    876
    -0.10
     burned
    -0.10
     condition
    -0.09
     privile
    -0.09
    gb
    -0.09
    736
    -0.09
    लब
    -0.09
    tek
    -0.09
     Wells
    -0.09
    POSITIVE LOGITS
     threatened
    0.40
     threat
    0.34
     endangered
    0.31
    -threat
    0.30
     threats
    0.30
     Threat
    0.29
    threat
    0.28
     danger
    0.27
     threaten
    0.26
     jeopardy
    0.21
    Activations Density 0.130%

    No Known Activations