© 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. 29893
    Prev
    Next
    INDEX
    Explanations

    potential harm and its causes

    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
    ahr
    -0.11
    acos
    -0.09
    anki
    -0.09
     effected
    -0.09
     endemic
    -0.08
    phalt
    -0.08
    vig
    -0.08
    ISCO
    -0.08
    .commons
    -0.08
     件
    -0.08
    POSITIVE LOGITS
     caused
    0.27
     CAUSED
    0.19
     cause
    0.17
     způsob
    0.17
     пÑĢиÑĩин
    0.17
     gây
    0.16
     occasion
    0.16
    éĢłæĪIJ
    0.16
     causes
    0.16
    cause
    0.16
    Activations Density 0.075%

    No Known Activations