© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 42919
    Prev
    Next
    INDEX
    Explanations

    hope for future outcomes

    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
     likely
    -0.13
     almost
    -0.12
     Likely
    -0.11
    likely
    -0.11
     probably
    -0.11
    almost
    -0.10
     certain
    -0.10
    ripp
    -0.10
    æģIJ
    -0.09
     sure
    -0.09
    POSITIVE LOGITS
     soon
    0.19
    soon
    0.14
    èĥ½
    0.14
     able
    0.13
     enough
    0.12
     Soon
    0.12
    èĩ³å°ij
    0.12
     alespoÅĪ
    0.12
    Soon
    0.12
     ÑħоÑĤÑı
    0.12
    Activations Density 0.050%

    No Known Activations