© 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. 38950
    Prev
    Next
    INDEX
    Explanations

    audio effects and plugins

    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
    dz
    -0.11
     coll
    -0.10
     gou
    -0.09
     rest
    -0.09
    elyn
    -0.09
     shades
    -0.09
    inkel
    -0.09
    esimal
    -0.08
    SENSOR
    -0.08
     Translation
    -0.08
    POSITIVE LOGITS
     rever
    0.23
     delay
    0.22
     echo
    0.17
     Delay
    0.17
     delays
    0.16
     tails
    0.15
     Rever
    0.15
     spatial
    0.15
     wet
    0.15
    Delay
    0.15
    Activations Density 0.022%

    No Known Activations