© 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. 44466
    Prev
    Next
    INDEX
    Explanations

    disappearing, vanished, missing

    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
    lag
    -0.09
    STA
    -0.09
    basket
    -0.09
    ometr
    -0.09
    åĩºæĿ¥
    -0.09
    ä¸ĢåĮº
    -0.08
    è¿
    -0.08
    ä¸į足
    -0.08
    /lic
    -0.08
     basket
    -0.08
    POSITIVE LOGITS
     into
    0.16
    van
    0.15
     disappeared
    0.15
     disappearance
    0.15
    æ¶Ī
    0.13
    ances
    0.13
     Into
    0.13
     иÑģÑĩ
    0.13
     thin
    0.12
     disappear
    0.12
    Activations Density 0.038%

    No Known Activations