© 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. 22008
    Prev
    Next
    INDEX
    Explanations

    exploring, entre, a, its, some

    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
    IIIK
    -0.09
    ******č\n
    -0.08
    TRGL
    -0.08
    ifax
    -0.08
    éĢģæĸĻ
    -0.08
    (IntPtr
    -0.08
    peria
    -0.08
    oggler
    -0.08
     Ñģигн
    -0.07
    <|begin_of_text|>
    -0.07
    POSITIVE LOGITS
    Âł
    0.09
    ASTE
    0.08
    ÂłP
    0.08
    λεκ
    0.08
    _plural
    0.07
    P
    0.07
    Unnamed
    0.07
    -B
    0.07
     plural
    0.07
    -b
    0.07
    Activations Density 0.043%

    No Known Activations