© 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. 15349
    Prev
    Next
    INDEX
    Explanations

    lack of coherence or standards

    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
     tutor
    -0.12
     teaches
    -0.10
     prec
    -0.10
     Housing
    -0.10
     classroom
    -0.10
     housing
    -0.09
     instructor
    -0.09
     Spoon
    -0.09
    aurant
    -0.09
     Tactics
    -0.09
    POSITIVE LOGITS
     UNESCO
    0.16
     Ed
    0.15
     Education
    0.15
    Education
    0.14
    EFA
    0.14
    Descriptors
    0.14
     ped
    0.13
     HE
    0.13
     ed
    0.13
     Quality
    0.13
    Activations Density 0.082%

    No Known Activations