© 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. 34001
    Prev
    Next
    INDEX
    Explanations

    release of versions and dates

    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
    uxt
    -0.10
    reme
    -0.10
    alc
    -0.09
     feathers
    -0.09
    iegel
    -0.09
    ormsg
    -0.09
    aceous
    -0.09
    nt
    -0.09
     migrationBuilder
    -0.09
    olley
    -0.09
    POSITIVE LOGITS
    .Release
    0.13
    hold
    0.11
    _notes
    0.11
    068
    0.11
    es
    0.10
     Notes
    0.10
    arking
    0.10
     date
    0.10
    ibility
    0.10
    iveness
    0.10
    Activations Density 0.019%

    No Known Activations