© 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
    5. 50-RESID-POST-GF
    7. 37957
    Prev
    Next
    INDEX
    Explanations

    direction and target

    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
    sto
    -0.11
    urette
    -0.10
    fo
    -0.09
     dafür
    -0.09
    ician
    -0.09
    ableView
    -0.09
    jack
    -0.09
     Hatch
    -0.08
    GOR
    -0.08
    rio
    -0.08
    POSITIVE LOGITS
    ness
    0.14
     towards
    0.12
    /generated
    0.11
     toward
    0.11
     entirely
    0.11
    epend
    0.10
    ãĥ¼ãĥ¼
    0.10
    elic
    0.10
    riv
    0.09
     riv
    0.09
    Activations Density 0.088%

    No Known Activations