© 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 (Instruct)
    5. 50-RESID-POST-GF
    7. 38555
    Prev
    Next
    INDEX
    Explanations

    historian and writer

    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
     hollow
    -0.10
    ä¹Ĥ
    -0.09
    ffen
    -0.09
    aminer
    -0.09
    ResourceManager
    -0.09
    InstanceState
    -0.09
    argo
    -0.08
     legacy
    -0.08
    onse
    -0.08
     ><?
    -0.08
    POSITIVE LOGITS
     History
    0.20
     Histor
    0.19
     historians
    0.19
     histor
    0.18
     historian
    0.18
     hist
    0.18
     history
    0.17
    History
    0.17
     Hist
    0.17
     histoire
    0.16
    Activations Density 0.089%

    No Known Activations