© 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. 42178
    Prev
    Next
    INDEX
    Explanations

    what comes after "with" or ends/begins

    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
    comings
    -0.11
    ipro
    -0.09
    å¤ĩ
    -0.09
    onec
    -0.08
     Suff
    -0.08
     Truman
    -0.08
    apro
    -0.08
    ofilm
    -0.08
    gnore
    -0.08
     Ames
    -0.08
    POSITIVE LOGITS
     bang
    0.25
    bang
    0.21
     Bang
    0.19
     flourish
    0.18
    Bang
    0.17
     whim
    0.17
     cliff
    0.17
     note
    0.14
     promise
    0.12
     Hook
    0.12
    Activations Density 0.032%

    No Known Activations