© 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
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 44493
    Prev
    Next
    INDEX
    Explanations

    secure protocols and authentication

    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
     security
    -0.16
    -security
    -0.14
    Security
    -0.13
     Security
    -0.12
    security
    -0.12
    _SECURITY
    -0.11
    _security
    -0.11
    iness
    -0.11
     SECURITY
    -0.11
     securities
    -0.11
    POSITIVE LOGITS
    auc
    0.14
    ment
    0.13
     hã
    0.12
     chắn
    0.12
    CRT
    0.12
    ments
    0.12
    fty
    0.12
    ly
    0.12
    zza
    0.12
    ncy
    0.11
    Activations Density 0.021%

    No Known Activations