© 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. 34149
    Prev
    Next
    INDEX
    Explanations

    introducing a description

    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
     evidenced
    -0.17
     evid
    -0.11
     Evidence
    -0.09
    asmus
    -0.09
     incident
    -0.09
    ep
    -0.09
    ictured
    -0.09
    ihu
    -0.08
    ays
    -0.08
    ched
    -0.08
    POSITIVE LOGITS
     far
    0.16
    phy
    0.16
     soon
    0.14
    ides
    0.14
     usual
    0.14
     daleko
    0.12
    soon
    0.11
    cert
    0.11
     luck
    0.11
    mode
    0.11
    Activations Density 0.045%

    No Known Activations