© 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. 5129
    Prev
    Next
    INDEX
    Explanations

    encroaching on a nearby

    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
    uter
    -0.10
     hide
    -0.09
    ĥ
    -0.09
     Laurent
    -0.09
    dition
    -0.09
    å»
    -0.08
    mut
    -0.08
    vecs
    -0.08
    untu
    -0.08
    validation
    -0.08
    POSITIVE LOGITS
     sensitive
    0.30
    -sensitive
    0.23
     delicate
    0.23
     fragile
    0.23
    Sensitive
    0.19
    æķı
    0.19
    ensitive
    0.18
     vulnerable
    0.15
     valuable
    0.15
    frag
    0.15
    Activations Density 0.094%

    No Known Activations