© 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. 38672
    Prev
    Next
    INDEX
    Explanations

    facing challenges and decision making

    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
    r
    -0.09
     relief
    -0.09
     Philip
    -0.09
     apocalypse
    -0.09
    <
    -0.08
     ant
    -0.08
     confronting
    -0.08
     rock
    -0.08
     nowhere
    -0.08
    _SECURE
    -0.08
    POSITIVE LOGITS
     face
    0.19
     encounter
    0.18
    éģ¿
    0.17
    éģĩ
    0.17
     Avoid
    0.17
     fight
    0.17
    Avoid
    0.16
    avoid
    0.15
     deal
    0.15
    Dod
    0.15
    Activations Density 0.058%

    No Known Activations