© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 45130
    Prev
    Next
    INDEX
    Explanations

    set of rules

    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
    ampo
    -0.09
    utenberg
    -0.09
     subclasses
    -0.09
     Ago
    -0.09
    IGHL
    -0.09
     Literal
    -0.08
    itere
    -0.08
    acman
    -0.08
     Gesture
    -0.08
    estroy
    -0.08
    POSITIVE LOGITS
     typing
    0.15
     Hind
    0.15
     type
    0.15
     polym
    0.15
    /type
    0.14
     Type
    0.14
     Pierce
    0.13
    typing
    0.13
     Ty
    0.13
     Typ
    0.12
    Activations Density 0.051%

    No Known Activations