© 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. 34556
    Prev
    Next
    INDEX
    Explanations

    mountain climbing and peaks

    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
     MVP
    -0.11
    лÑİ
    -0.10
    å¸Ń
    -0.10
    ìĽĶë¶ĢíĦ°
    -0.10
    DTD
    -0.09
    323
    -0.09
     Mediterranean
    -0.09
    âĪł
    -0.09
    åĮ
    -0.09
     cata
    -0.09
    POSITIVE LOGITS
     summit
    0.26
     mount
    0.25
     Summit
    0.20
     Sher
    0.19
     summ
    0.18
     Base
    0.18
    æĶ
    0.17
     Mount
    0.17
     oxygen
    0.17
    çĻ»
    0.17
    Activations Density 0.049%

    No Known Activations