© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 57765
    Prev
    Next
    INDEX
    Explanations

    self-defense techniques such as strikes

    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
    ÄIJT
    -0.09
    ervo
    -0.09
    uner
    -0.09
     intros
    -0.09
     ServletException
    -0.09
    stro
    -0.09
    sla
    -0.08
    å¼
    -0.08
     stutter
    -0.08
    å°
    -0.08
    POSITIVE LOGITS
     pepper
    0.17
     defend
    0.17
     defending
    0.16
     defense
    0.16
     attacker
    0.15
     defence
    0.15
    -defense
    0.14
     defended
    0.14
     defender
    0.14
     attackers
    0.13
    Activations Density 0.050%

    No Known Activations