© 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. 33176
    Prev
    Next
    INDEX
    Explanations

    be safe or effective

    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
     aw
    -0.10
    _UI
    -0.10
     Morrow
    -0.09
     sisters
    -0.09
    Intialized
    -0.09
    !=(
    -0.09
     ab
    -0.09
     Spart
    -0.08
     Fors
    -0.08
     invent
    -0.08
    POSITIVE LOGITS
     safe
    0.37
    safe
    0.28
     Safe
    0.28
    -safe
    0.27
    Safe
    0.25
    å®īåħ¨
    0.23
     безопаÑģ
    0.23
     safer
    0.21
     SAFE
    0.21
    _safe
    0.20
    Activations Density 0.047%

    No Known Activations