© 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. 37993
    Prev
    Next
    INDEX
    Explanations

    degree or scope of a phrase

    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
    agal
    -0.09
    _PUSHDATA
    -0.09
    Doctrine
    -0.08
    akest
    -0.08
     huh
    -0.08
     кÑĥлÑĮÑĤÑĥ
    -0.08
    uars
    -0.08
    ermen
    -0.08
     strm
    -0.08
    pillar
    -0.08
    POSITIVE LOGITS
     somewhat
    0.11
     fairly
    0.10
     relatively
    0.10
     kind
    0.09
     unlikely
    0.09
     اختÙĦ
    0.09
    947
    0.08
     proverb
    0.08
    ft
    0.08
     pretty
    0.08
    Activations Density 0.167%

    No Known Activations