© 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. 62883
    Prev
    Next
    INDEX
    Explanations

    contrasting or alternatives

    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
     rather
    -0.33
    rather
    -0.25
     chứ
    -0.21
    ãģ§ãģ¯ãģªãģı
    -0.20
     Rather
    -0.20
     instead
    -0.19
    Rather
    -0.17
     вмеÑģÑĤ
    -0.15
    instead
    -0.15
     eher
    -0.14
    POSITIVE LOGITS
     alone
    0.15
     or
    0.15
     nor
    0.14
     like
    0.14
     necessarily
    0.14
     anymore
    0.14
    alone
    0.13
     Alone
    0.12
     ones
    0.11
    nor
    0.10
    Activations Density 0.114%

    No Known Activations