© 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. 35499
    Prev
    Next
    INDEX
    Explanations

    numbers followed by symbols or descriptions

    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
    ụy
    -0.10
     Gig
    -0.10
    aland
    -0.10
    ekim
    -0.09
    gorith
    -0.09
     (<
    -0.09
    opis
    -0.09
     migrationBuilder
    -0.09
    vez
    -0.09
    iker
    -0.08
    POSITIVE LOGITS
    -minus
    0.13
     minus
    0.11
    minus
    0.10
     maximum
    0.09
     bra
    0.09
     BRA
    0.09
     Pact
    0.09
     Fence
    0.09
     ob
    0.08
     Clarke
    0.08
    Activations Density 0.134%

    No Known Activations