© 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. 44517
    Prev
    Next
    INDEX
    Explanations

    technical and proper names

    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
    ¦
    -0.09
    ศà¸Ī
    -0.09
    ERGE
    -0.09
    ､:
    -0.09
     Rah
    -0.08
     McCorm
    -0.08
    $MESS
    -0.08
    uchen
    -0.08
    ÂŁ
    -0.08
     enr
    -0.08
    POSITIVE LOGITS
    avra
    0.08
     pulumi
    0.08
     Ernst
    0.08
    slack
    0.08
    igma
    0.07
    herits
    0.07
     Cornel
    0.07
    ses
    0.07
    ControlItem
    0.07
     Wie
    0.07
    Activations Density 0.023%

    No Known Activations