© 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. 35149
    Prev
    Next
    INDEX
    Explanations

    is not

    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
     slightly
    -0.15
    æľīçĤ¹
    -0.13
     hơi
    -0.12
     somewhat
    -0.11
    è¾ĥ
    -0.10
     немного
    -0.10
     relatively
    -0.09
     blatantly
    -0.09
    éĥ
    -0.09
     vain
    -0.09
    POSITIVE LOGITS
     completely
    0.22
     absolutely
    0.19
     definitely
    0.19
    å®Įåħ¨
    0.18
     far
    0.18
    æł¹æľ¬
    0.18
    pletely
    0.17
     entirely
    0.16
     kesinlikle
    0.16
     hoÃłn
    0.15
    Activations Density 0.160%

    No Known Activations