© 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. 9792
    Prev
    Next
    INDEX
    Explanations

    recognizes sequences like "point mutant"

    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
    ÅĻád
    -0.09
    ekim
    -0.08
    ntax
    -0.08
    ONSE
    -0.07
    ="{!!
    -0.07
    ĮĴ
    -0.07
    _Lean
    -0.07
    łéĻ¤
    -0.07
    vÄĽÅĻ
    -0.07
    ((((
    -0.07
    POSITIVE LOGITS
     aforementioned
    0.10
     _{}
    0.09
     afore
    0.09
    ÂŃi
    0.07
    ModelProperty
    0.07
     Ä°mpar
    0.07
    /////
    0.07
    &apos
    0.07
    ĻĤ
    0.06
     prob
    0.06
    Activations Density 1.187%

    No Known Activations