© 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. 61034
    Prev
    Next
    INDEX
    Explanations

    condition leading to prevention

    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
    ignet
    -0.10
     Morse
    -0.09
     Dil
    -0.09
    Absent
    -0.09
    Nos
    -0.09
    inator
    -0.09
     |_|
    -0.09
    νοι
    -0.09
    rzy
    -0.08
    ocale
    -0.08
    POSITIVE LOGITS
    导èĩ´
    0.16
     causing
    0.15
     cause
    0.15
     caused
    0.13
     causes
    0.12
     could
    0.12
    cause
    0.12
     may
    0.12
     prevents
    0.11
     resulting
    0.11
    Activations Density 0.047%

    No Known Activations