© 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. 58189
    Prev
    Next
    INDEX
    Explanations

    consider investing

    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
    ê±°ëŀĺê°Ģ
    -0.08
     foregoing
    -0.08
    .Companion
    -0.07
    aret
    -0.07
    езÑĥлÑĮÑĤ
    -0.07
     nackte
    -0.07
    )did
    -0.07
    .::
    -0.07
    orgetown
    -0.07
    rière
    -0.07
    POSITIVE LOGITS
    以ä¸ĭ
    0.31
     below
    0.28
     Below
    0.26
    Below
    0.24
    å¦Ĥä¸ĭ
    0.24
    below
    0.21
     following
    0.20
     BELOW
    0.19
    .Here
    0.18
    :\n
    0.18
    Activations Density 1.161%

    No Known Activations