© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 34997
    Prev
    Next
    INDEX
    Explanations

    cannot believe

    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
     muster
    -0.12
     Leonard
    -0.09
     QName
    -0.09
    lix
    -0.09
    IFA
    -0.09
     Ops
    -0.08
    رÙħ
    -0.08
    ifiable
    -0.08
    _PY
    -0.08
     Dudley
    -0.08
    POSITIVE LOGITS
     believe
    0.33
     believes
    0.24
     Believe
    0.23
    çĽ¸ä¿¡
    0.23
     believed
    0.23
     belief
    0.22
    belie
    0.19
     believing
    0.19
    belief
    0.17
     believer
    0.16
    Activations Density 0.014%

    No Known Activations