© 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. 38635
    Prev
    Next
    INDEX
    Explanations

    ich bin auf

    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
     bekan
    -0.12
     dara
    -0.11
    andon
    -0.11
    tring
    -0.10
     statt
    -0.10
    endon
    -0.09
    idon
    -0.09
    zend
    -0.09
    OSE
    -0.09
    eda
    -0.09
    POSITIVE LOGITS
     завиÑģим
    0.14
     glad
    0.12
     hil
    0.12
    abei
    0.11
     fro
    0.10
     legitim
    0.10
    adow
    0.10
     gut
    0.10
    icari
    0.10
    nte
    0.09
    Activations Density 0.061%

    No Known Activations