© 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. 52086
    Prev
    Next
    INDEX
    Explanations

    how obscure, a type, different things

    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
     content
    -0.10
    èĤī
    -0.09
     retrospective
    -0.09
    ç²Ĵ
    -0.09
    fffffff
    -0.08
    ãĢĢ ãĢĢ ãĢĢ ãĢĢ
    -0.08
     tern
    -0.08
     invisible
    -0.08
     driving
    -0.08
     Orb
    -0.08
    POSITIVE LOGITS
     objects
    0.38
     object
    0.33
     Objects
    0.31
    objects
    0.29
     objetos
    0.27
     обÑĬекÑĤ
    0.26
    object
    0.26
    Objects
    0.25
    对象
    0.25
    çī©
    0.24
    Activations Density 0.276%

    No Known Activations