© 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. 1966
    Prev
    Next
    INDEX
    Explanations

    concepts and topics

    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
     indeed
    -0.11
     shall
    -0.11
    dings
    -0.10
     equals
    -0.09
    ｡
    -0.09
    ahren
    -0.09
     slightly
    -0.08
    ANTE
    -0.08
     seemingly
    -0.08
    .Meta
    -0.08
    POSITIVE LOGITS
     å¹
    0.09
    è±Ĩ
    0.09
    isser
    0.08
    Â
    0.08
     ausp
    0.08
     alike
    0.08
     merc
    0.08
     badly
    0.08
     writ
    0.08
    za
    0.08
    Activations Density 0.052%

    No Known Activations