© 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. 33682
    Prev
    Next
    INDEX
    Explanations

    the beginning of definitive statements

    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
    Disappear
    -0.10
    2
    -0.09
    266
    -0.08
     Naj
    -0.08
    ittest
    -0.08
    liest
    -0.08
    ôt
    -0.08
     EntryPoint
    -0.08
     renamed
    -0.08
    uele
    -0.08
    POSITIVE LOGITS
     answer
    0.21
    oret
    0.19
    orem
    0.18
     question
    0.17
     short
    0.17
    ories
    0.16
    answer
    0.16
     term
    0.16
    irs
    0.16
    atre
    0.15
    Activations Density 0.147%

    No Known Activations