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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 30985
    Prev
    Next
    INDEX
    Explanations

    English translation or name

    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
     alphabetical
    -0.12
     nouns
    -0.12
     prefixes
    -0.11
    alphabet
    -0.11
     åŃĹ
    -0.11
    åŃĹ
    -0.10
     Prefix
    -0.10
     surname
    -0.10
     alphabet
    -0.10
     vocab
    -0.10
    POSITIVE LOGITS
     alternate
    0.18
     Ali
    0.18
     alternative
    0.18
     spell
    0.18
     full
    0.17
     ali
    0.16
     alias
    0.16
    (alias
    0.16
     Spell
    0.15
    spell
    0.15
    Activations Density 0.256%

    No Known Activations