© 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. 30385
    Prev
    Next
    INDEX
    Explanations

    ability and possibility

    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
     поба
    -0.10
     Cant
    -0.10
    éłĪ
    -0.09
    å¿ħé¡»
    -0.09
     outr
    -0.08
    _ALIGN
    -0.08
     Canterbury
    -0.08
     undo
    -0.08
    KG
    -0.08
    OOT
    -0.08
    POSITIVE LOGITS
     can
    0.21
    åı¯ä»¥
    0.17
     dapat
    0.16
     können
    0.15
    abilirsiniz
    0.14
     pouvez
    0.14
    èĥ½å¤Ł
    0.14
     можеÑĤе
    0.14
     possono
    0.14
     kunnen
    0.13
    Activations Density 0.014%

    No Known Activations