© 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. 53749
    Prev
    Next
    INDEX
    Explanations

    sentences beginning with this

    np_acts-logits-general · gemini-2.5-flash-lite

    sentence or clause boundaries, particularly after commas, conjunctions, or at the start of new statements.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @yooniel31
    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
    anten
    -0.09
    itti
    -0.08
    ORIZ
    -0.08
     dara
    -0.08
    rey
    -0.08
     Bald
    -0.08
    rox
    -0.08
    yz
    -0.08
     cha
    -0.08
     NotImplemented
    -0.08
    POSITIVE LOGITS
     this
    0.37
    this
    0.32
     This
    0.29
    This
    0.28
    \tthis
    0.27
     nÃły
    0.27
     THIS
    0.27
    è¿Ļ
    0.25
    -this
    0.25
    ,this
    0.25
    Activations Density 0.040%

    No Known Activations