© 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. 36199
    Prev
    Next
    INDEX
    Explanations

    many or countless activities

    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
    ä½ķãģĭ
    -0.09
     Certain
    -0.09
     EITHER
    -0.08
     nÄĽk
    -0.08
    æŁIJ
    -0.08
    ëį°ìĿ´íĬ¸
    -0.08
    /from
    -0.08
     glimpse
    -0.08
    ENTIAL
    -0.08
     etwas
    -0.08
    POSITIVE LOGITS
     various
    0.21
    åIJĦç§į
    0.20
     numerous
    0.19
     several
    0.18
     increasingly
    0.17
     Various
    0.16
     scores
    0.15
     every
    0.15
     dozens
    0.14
     all
    0.14
    Activations Density 0.086%

    No Known Activations