© 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. 38033
    Prev
    Next
    INDEX
    Explanations

    company industries reputation

    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
    633
    -0.10
     scenery
    -0.09
    arendra
    -0.09
     ingest
    -0.09
    rij
    -0.09
     duk
    -0.09
    ulong
    -0.09
     Fitzgerald
    -0.09
    ombie
    -0.09
    anke
    -0.09
    POSITIVE LOGITS
     bag
    0.12
    Exports
    0.12
     pan
    0.11
     tie
    0.10
     cat
    0.10
     fel
    0.10
     vide
    0.10
     rop
    0.10
     improvised
    0.10
     barg
    0.09
    Activations Density 0.077%

    No Known Activations