© 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. 23901
    Prev
    Next
    INDEX
    Explanations

    knew she'd or mother loved

    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
    elm
    -0.11
     actually
    -0.10
    à¹Ģลย
    -0.10
    abcdefghijklmnop
    -0.10
    urr
    -0.10
     à¤ĩतन
    -0.09
    ABCDEFGHIJKLMNOP
    -0.09
    åĪ°åºķ
    -0.09
    opr
    -0.09
     Arte
    -0.09
    POSITIVE LOGITS
     probably
    0.18
     likely
    0.14
     Probably
    0.14
    Probably
    0.12
     unlikely
    0.12
    probably
    0.12
     capable
    0.12
    likely
    0.11
     risks
    0.11
    FFE
    0.10
    Activations Density 0.032%

    No Known Activations