© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 4949
    Prev
    Next
    INDEX
    Explanations

    including or just

    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
    .CONFIG
    -0.10
    arpa
    -0.09
    umba
    -0.09
    urt
    -0.09
    ãĢĢr
    -0.09
    isan
    -0.09
    ToDevice
    -0.08
    487
    -0.08
    elda
    -0.08
     organisms
    -0.08
    POSITIVE LOGITS
     audio
    0.15
     monetary
    0.11
     food
    0.11
    audio
    0.10
     guitar
    0.10
    éĻĨ
    0.10
     verbal
    0.10
     electricity
    0.10
     AUDIO
    0.10
     aviation
    0.09
    Activations Density 0.315%

    No Known Activations