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. 64984
    Prev
    Next
    INDEX
    Explanations

    summary factual consistency criteria

    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
    ãģĬãĤĬ
    -0.12
    sWith
    -0.10
     SPELL
    -0.09
    ely
    -0.09
    ühl
    -0.09
    asal
    -0.08
     ÙĦغ
    -0.08
    undef
    -0.08
    롱
    -0.08
    yh
    -0.08
    POSITIVE LOGITS
     statement
    0.12
     sentence
    0.11
     Statement
    0.11
    (summary
    0.11
     rash
    0.10
    371
    0.09
     Abed
    0.09
     claim
    0.09
    yy
    0.09
    /Main
    0.09
    Activations Density 0.022%

    No Known Activations