© 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. 50655
    Prev
    Next
    INDEX
    Explanations

    syntax, semantics, features, structure, API

    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
     playbook
    -0.09
    é¾
    -0.09
    Locale
    -0.09
    aul
    -0.09
     scenario
    -0.09
    _locale
    -0.09
    psilon
    -0.09
     Klaus
    -0.09
     region
    -0.08
     prototype
    -0.08
    POSITIVE LOGITS
     philosophy
    0.21
     architecture
    0.17
    phil
    0.17
    åĵ²
    0.16
     structure
    0.16
     Philosophy
    0.16
     syntax
    0.16
     API
    0.15
    yntax
    0.14
     approach
    0.14
    Activations Density 0.127%

    No Known Activations