© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 1307
    Prev
    Next
    INDEX
    Explanations

    counter-terrorism, crime, hate speech

    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
     jihadist
    -0.14
     jih
    -0.12
     jihadists
    -0.11
     Jihad
    -0.11
     jihad
    -0.10
    eki
    -0.10
    archy
    -0.10
     Shiite
    -0.09
     clo
    -0.09
     Allah
    -0.09
    POSITIVE LOGITS
    CVE
    0.17
     CVE
    0.17
     counter
    0.15
     Counter
    0.14
    (counter
    0.14
    -rad
    0.13
     radical
    0.13
    izmet
    0.13
     conveyor
    0.13
     Radical
    0.12
    Activations Density 0.025%

    No Known Activations