© 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. 26850
    Prev
    Next
    INDEX
    Explanations

    its role or significance

    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
    vale
    -0.11
    oron
    -0.10
    enaire
    -0.09
     proto
    -0.08
    dden
    -0.08
    orea
    -0.08
    REFERENCE
    -0.08
    urname
    -0.08
     dol
    -0.08
    ager
    -0.08
    POSITIVE LOGITS
     relation
    0.25
     role
    0.21
     relationship
    0.19
    relation
    0.18
     Relation
    0.17
    role
    0.16
     connection
    0.14
    lef
    0.14
     application
    0.14
     applications
    0.14
    Activations Density 0.037%

    No Known Activations