© 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. 2125
    Prev
    Next
    INDEX
    Explanations

    assumptions about factors

    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
     Gibbs
    -0.09
     Aggregate
    -0.09
     innocence
    -0.09
    Aggregate
    -0.09
     Friedman
    -0.08
     vic
    -0.08
    åĪĴ
    -0.08
     Rotation
    -0.08
     score
    -0.08
    addir
    -0.08
    POSITIVE LOGITS
     assumptions
    0.27
     assumption
    0.22
     inputs
    0.22
     input
    0.21
     assumed
    0.18
     Inputs
    0.17
     Ass
    0.17
     assum
    0.16
     Input
    0.15
    input
    0.15
    Activations Density 0.131%

    No Known Activations