Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 38347
    Prev
    Next
    INDEX
    Explanations

    vamos mostrar

    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
     nuest
    -0.13
     typ
    -0.11
     ya
    -0.10
     pione
    -0.09
     ill
    -0.09
     grátis
    -0.09
     eventually
    -0.09
     myself
    -0.09
     Ann
    -0.09
     sustained
    -0.09
    POSITIVE LOGITS
     pornô
    0.15
     protagon
    0.14
     pornôs
    0.11
    iê
    0.10
     drib
    0.10
     pont
    0.10
    raç
    0.09
    gressor
    0.09
     NodeType
    0.09
     tô
    0.09
    Activations Density 0.358%

    No Known Activations