© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 1351
    Prev
    Next
    INDEX
    Explanations

    explaining subsequent states

    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
     ign
    -0.11
    ÑĭваеÑĤ
    -0.10
    Joined
    -0.10
    ê¸Ķ
    -0.10
    uje
    -0.10
    nave
    -0.10
     ignited
    -0.10
     aff
    -0.10
    ÑĭваÑİÑĤ
    -0.09
    issent
    -0.09
    POSITIVE LOGITS
     was
    0.17
     gave
    0.16
     cost
    0.14
    was
    0.14
     did
    0.13
     allowed
    0.13
     ent
    0.12
     بÙĪد
    0.12
     resulted
    0.12
     дли
    0.12
    Activations Density 0.099%

    No Known Activations