© 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. 25830
    Prev
    Next
    INDEX
    Explanations

    connecting clauses and ideas

    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
    848
    -0.10
    742
    -0.09
     IMPLIED
    -0.09
     Tru
    -0.08
    ography
    -0.08
     compromises
    -0.08
     име
    -0.08
    172
    -0.08
    alf
    -0.08
    _example
    -0.08
    POSITIVE LOGITS
     allow
    0.19
     khiến
    0.19
     allows
    0.16
     allowing
    0.16
     заÑģÑĤав
    0.15
     позволÑıеÑĤ
    0.15
    à¸Ĺำà¹ĥห
    0.14
     allowed
    0.14
    使
    0.14
     causing
    0.13
    Activations Density 0.107%

    No Known Activations