© 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. 30883
    Prev
    Next
    INDEX
    Explanations

    identity theft, cyber attacks, drug addiction, public sex

    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
     disrupt
    -0.11
     Gry
    -0.10
    »
    -0.09
     situation
    -0.09
    amen
    -0.09
    ronics
    -0.09
    avan
    -0.09
    505
    -0.08
    anza
    -0.08
    är
    -0.08
    POSITIVE LOGITS
    -related
    0.16
    ophobia
    0.11
     exposure
    0.11
     related
    0.11
    -induced
    0.11
    osis
    0.10
    icide
    0.10
    Intialized
    0.10
    omnia
    0.10
    flation
    0.10
    Activations Density 0.127%

    No Known Activations