© 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. 51551
    Prev
    Next
    INDEX
    Explanations

    transforming into something

    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
    ForResult
    -0.10
     ​​
    -0.09
    iram
    -0.09
    aar
    -0.09
    ABL
    -0.09
    иÑĢÑĥ
    -0.09
    족
    -0.09
    pdata
    -0.09
    Å¡ÃŃ
    -0.08
    isbury
    -0.08
    POSITIVE LOGITS
    ations
    0.23
    ative
    0.20
    al
    0.18
    atted
    0.15
    ATIONS
    0.14
     into
    0.13
    into
    0.13
    e
    0.13
    asi
    0.12
    (Transform
    0.12
    Activations Density 0.026%

    No Known Activations