© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 23918
    Prev
    Next
    INDEX
    Explanations

    solid state and formation

    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
    ãģĬãĤĬ
    -0.12
     Mitar
    -0.10
    zug
    -0.09
    owitz
    -0.09
    iej
    -0.09
    ValueCollection
    -0.09
    ynom
    -0.09
     Mastery
    -0.09
    eso
    -0.09
    <|begin_of_text|>
    -0.08
    POSITIVE LOGITS
    ified
    0.28
    ifying
    0.26
    ly
    0.24
    arity
    0.23
    ifies
    0.22
    ify
    0.21
    -state
    0.21
    ification
    0.21
    -solid
    0.20
    ary
    0.19
    Activations Density 0.016%

    No Known Activations