© 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. 40401
    Prev
    Next
    INDEX
    Explanations

    managing or stopping progression

    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
     amel
    -0.11
     Hugo
    -0.10
    ï½Ĭ
    -0.09
     âĩĴ
    -0.09
    jq
    -0.09
    acio
    -0.08
    zf
    -0.08
     ëĭ
    -0.08
    obel
    -0.08
    æĬ¤
    -0.08
    POSITIVE LOGITS
     rem
    0.20
     improvement
    0.18
     improvements
    0.17
     Improvement
    0.16
    å¥ı
    0.15
     durable
    0.15
    Impro
    0.15
     reductions
    0.14
     Impro
    0.14
     rel
    0.14
    Activations Density 0.047%

    No Known Activations