© 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. 44728
    Prev
    Next
    INDEX
    Explanations

    broken leg

    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
    æĬ¬
    -0.10
    ril
    -0.10
    ayer
    -0.09
     perg
    -0.09
     Lah
    -0.09
     beaut
    -0.09
     Roh
    -0.09
     kl
    -0.09
    _packages
    -0.09
    ainless
    -0.08
    POSITIVE LOGITS
     toy
    0.32
     toys
    0.30
     doll
    0.29
     dolls
    0.29
    toy
    0.24
    Toy
    0.24
    doll
    0.23
     Doll
    0.23
     Toy
    0.22
     plush
    0.22
    Activations Density 0.085%

    No Known Activations