© 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. 30296
    Prev
    Next
    INDEX
    Explanations

    preposition followed by articles or possessives

    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
    ¦æĥħ
    -0.10
    įng
    -0.10
    .Formatter
    -0.09
     accord
    -0.09
    ubre
    -0.09
    ¶Į
    -0.08
    engu
    -0.08
    ÄįasÃŃ
    -0.08
    éĤ£äºĽ
    -0.08
    çĴ
    -0.08
    POSITIVE LOGITS
     the
    0.11
    the
    0.09
    ãĢģãĢģ
    0.09
     your
    0.08
    your
    0.08
     VÅ¡ech
    0.08
     Bark
    0.08
    ope
    0.08
    to
    0.08
     Continue
    0.08
    Activations Density 0.083%

    No Known Activations