© 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. 129
    Prev
    Next
    INDEX
    Explanations

    that being said

    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
    addir
    -0.10
     retro
    -0.09
    ensch
    -0.09
    SION
    -0.09
    985
    -0.09
    ãĥ»ãĥ»ãĥ»\n\n
    -0.09
    iosa
    -0.08
    å¾ģ
    -0.08
     laut
    -0.08
    scan
    -0.08
    POSITIVE LOGITS
     said
    0.49
    said
    0.37
     Said
    0.29
     sagte
    0.25
     saying
    0.24
     dicho
    0.23
     Ñģказал
    0.22
     à¤ķह
    0.21
     dijo
    0.20
     having
    0.19
    Activations Density 0.026%

    No Known Activations