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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 449
    Prev
    Next
    INDEX
    Explanations

    can lead to negative outcomes

    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
     поба
    -0.13
    é»İ
    -0.10
     Freem
    -0.10
     Grü
    -0.09
    ÄĻd
    -0.08
     zost
    -0.08
     завиÑģим
    -0.08
    dap
    -0.08
    _filepath
    -0.08
    æ¡£
    -0.08
    POSITIVE LOGITS
     lead
    0.14
     cause
    0.14
    cause
    0.12
     result
    0.12
     leads
    0.12
     resulted
    0.12
     led
    0.12
     health
    0.11
     risks
    0.11
     causes
    0.11
    Activations Density 0.016%

    No Known Activations