© 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. 29767
    Prev
    Next
    INDEX
    Explanations

    discutir e fazer recomendações

    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
    oha
    -0.10
     dedic
    -0.09
    기ê´Ģ
    -0.09
    å´
    -0.09
    uthor
    -0.09
    äºĭæ¥Ń
    -0.08
     surre
    -0.08
     solicit
    -0.08
     brick
    -0.08
     blond
    -0.08
    POSITIVE LOGITS
     training
    0.13
    valor
    0.13
     valor
    0.13
     research
    0.13
     perfection
    0.13
     control
    0.12
     Lobby
    0.12
     surveillance
    0.12
    training
    0.11
    control
    0.11
    Activations Density 0.127%

    No Known Activations