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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 45264
    Prev
    Next
    INDEX
    Explanations

    firearms manufacturing and soldier descriptions

    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
     Pistol
    -0.22
     pistol
    -0.22
     pistols
    -0.21
     handguns
    -0.20
     handgun
    -0.19
     revolver
    -0.18
     bullets
    -0.17
     Bullet
    -0.17
     bullet
    -0.17
     Glock
    -0.16
    POSITIVE LOGITS
     Brow
    0.18
     chamber
    0.17
     Rem
    0.16
    870
    0.14
     Moss
    0.14
     pump
    0.14
     bore
    0.14
     gauge
    0.13
    lug
    0.13
     chambers
    0.13
    Activations Density 0.019%

    No Known Activations