© 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. 44725
    Prev
    Next
    INDEX
    Explanations

    still present, take risks, most afraid

    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
    Lorem
    -0.08
     [~,
    -0.08
     Lorem
    -0.07
    ãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢ
    -0.07
    Unnamed
    -0.07
     initialValues
    -0.07
     Reminder
    -0.07
    /ay
    -0.06
    =explode
    -0.06
     Toe
    -0.06
    POSITIVE LOGITS
    оÑĢаÑı
    0.10
     müda
    0.08
     елем
    0.08
     ÑĤабли
    0.08
    ÑĢÑĸÑĪ
    0.08
    ModelProperty
    0.08
    ÑĸзнеÑģ
    0.08
    URLException
    0.07
    zbek
    0.07
    галÑĸ
    0.07
    Activations Density 2.514%

    No Known Activations