© 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. 33713
    Prev
    Next
    INDEX
    Explanations

    ahah sounds

    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
    _tC
    -0.12
    _mD
    -0.12
    _mE
    -0.12
    _tD
    -0.11
    _mC
    -0.11
    _Tis
    -0.11
    _tA
    -0.10
    _mB
    -0.10
    _tE
    -0.10
    /Dk
    -0.10
    POSITIVE LOGITS
     Bret
    0.08
     Sous
    0.08
    es
    0.08
     Guzzle
    0.08
    adele
    0.08
     Hra
    0.08
    اتÙĩ
    0.08
    .instant
    0.07
     Tato
    0.07
    nings
    0.07
    Activations Density 0.069%

    No Known Activations