© 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. 39599
    Prev
    Next
    INDEX
    Explanations

    immersive and addressing

    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
    agi
    -0.09
     (~(
    -0.09
    Introduced
    -0.09
     pÅĻeb
    -0.08
     concentrated
    -0.08
    bounce
    -0.08
     divert
    -0.08
     count
    -0.08
    ipa
    -0.08
    (
    -0.08
    POSITIVE LOGITS
     imm
    0.27
     immersion
    0.26
    imm
    0.24
     immer
    0.23
     Imm
    0.22
    -imm
    0.21
    immers
    0.21
     immersive
    0.20
    immer
    0.20
    Imm
    0.17
    Activations Density 0.069%

    No Known Activations