© 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. 33767
    Prev
    Next
    INDEX
    Explanations

    reading literature, create an, the sample

    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
    ¶Į
    -0.09
    ÂĢÂĢ
    -0.09
    ¦æĥħ
    -0.08
    łéĻ¤
    -0.08
    ￣￣￣￣￣￣￣￣
    -0.08
    ³ç´°
    -0.08
     btnSave
    -0.08
    Òij
    -0.08
    Ì
    -0.07
    olik
    -0.07
    POSITIVE LOGITS
     anything
    0.09
     âĹij
    0.09
     YYS
    0.08
     ragaz
    0.08
    anything
    0.08
    BEGIN
    0.07
    any
    0.07
     erotik
    0.07
     any
    0.07
     Begin
    0.07
    Activations Density 0.144%

    No Known Activations