© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 44708
    Prev
    Next
    INDEX
    Explanations

    promoting harmful or violent behavior

    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
     opport
    -0.12
     horn
    -0.11
    suppress
    -0.09
    aven
    -0.09
     EVP
    -0.09
    Suppress
    -0.09
    azo
    -0.09
    ï¼¹
    -0.09
     Opport
    -0.09
    utex
    -0.09
    POSITIVE LOGITS
     violence
    0.20
     inc
    0.18
     violent
    0.17
     cond
    0.17
     glor
    0.16
     advocacy
    0.16
     advocate
    0.15
     harm
    0.15
     Violence
    0.14
     threats
    0.14
    Activations Density 0.114%

    No Known Activations