© 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. 34661
    Prev
    Next
    INDEX
    Explanations

    keyboard modifier keys

    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
    reen
    -0.10
     Kern
    -0.10
     wet
    -0.09
     Indust
    -0.09
    (
    -0.09
     Axios
    -0.09
     RESET
    -0.08
    HB
    -0.08
     Dustin
    -0.08
     Dur
    -0.08
    POSITIVE LOGITS
     Alt
    0.29
    Alt
    0.24
     Shift
    0.24
     alt
    0.24
    Shift
    0.21
     ALT
    0.20
     shift
    0.20
    ALT
    0.18
    trl
    0.18
     press
    0.18
    Activations Density 0.075%

    No Known Activations