© 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. 43777
    Prev
    Next
    INDEX
    Explanations

    attack, pursue, prey

    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
    åĮ
    -0.10
     hungry
    -0.10
     attackers
    -0.10
     ourselves
    -0.09
     stranger
    -0.09
     ruthless
    -0.09
    .ribbon
    -0.09
    uli
    -0.09
    rada
    -0.08
     záb
    -0.08
    POSITIVE LOGITS
     victim
    0.24
     victims
    0.24
     innocent
    0.23
     Victim
    0.20
     hap
    0.19
    victim
    0.19
     Innoc
    0.19
     prey
    0.18
     innoc
    0.16
     Victims
    0.16
    Activations Density 0.143%

    No Known Activations