© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 43766
    Prev
    Next
    INDEX
    Explanations

    indicating or suggesting meaning

    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
    lander
    -0.10
    AZY
    -0.10
    -за
    -0.09
    mam
    -0.09
    çģ
    -0.08
    fad
    -0.08
    eza
    -0.08
    tern
    -0.08
    276
    -0.08
     Niet
    -0.08
    POSITIVE LOGITS
    说æĺİ
    0.20
     suggests
    0.19
    uggest
    0.18
     indicates
    0.16
     suggest
    0.16
    suggest
    0.16
     meaning
    0.16
     suggesting
    0.15
     což
    0.14
    meaning
    0.14
    Activations Density 0.105%

    No Known Activations