© 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. 40084
    Prev
    Next
    INDEX
    Explanations

    frost gives way, snow melts

    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
    .scalablytyped
    -0.11
     amel
    -0.09
     degradation
    -0.09
    óng
    -0.09
    ElementType
    -0.09
     plung
    -0.09
     deterioration
    -0.09
     darken
    -0.09
    icot
    -0.09
    rouch
    -0.08
    POSITIVE LOGITS
     gone
    0.22
    æ¶Ī
    0.21
     subs
    0.19
     Gone
    0.17
     diss
    0.17
     Van
    0.16
     away
    0.16
     van
    0.16
     VAN
    0.15
     rec
    0.15
    Activations Density 0.085%

    No Known Activations