Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 44861
    Prev
    Next
    INDEX
    Explanations

    bite or chewing

    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
     Chim
    -0.10
    lining
    -0.09
    ë³ij
    -0.09
    .biz
    -0.09
     assemblies
    -0.09
     Feet
    -0.09
    WWW
    -0.09
    asin
    -0.08
     handjob
    -0.08
    amina
    -0.08
    POSITIVE LOGITS
     lip
    0.20
    /stdc
    0.15
     bite
    0.15
    lip
    0.14
     biting
    0.14
     bitten
    0.13
     bit
    0.12
     Lip
    0.12
    bite
    0.12
     Bit
    0.12
    Activations Density 0.011%

    No Known Activations