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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 38785
    Prev
    Next
    INDEX
    Explanations

    language model

    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
    Model
    -0.12
    _model
    -0.12
     imper
    -0.11
     modeling
    -0.11
    Models
    -0.10
     models
    -0.10
     fle
    -0.10
     ph
    -0.10
     Modeling
    -0.10
     Models
    -0.10
    POSITIVE LOGITS
    led
    0.18
    ledon
    0.11
    ERSHEY
    0.10
    ë§ģ
    0.10
     Gim
    0.10
    876
    0.09
    urma
    0.09
    agem
    0.09
    (LL
    0.09
    HLT
    0.09
    Activations Density 0.057%

    No Known Activations