© 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. 34785
    Prev
    Next
    INDEX
    Explanations

    specific nouns

    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
     ìŀĪê³ł
    -0.10
     Verg
    -0.08
    iset
    -0.08
    -REAL
    -0.08
     Jew
    -0.08
     flick
    -0.08
    ulace
    -0.08
    519
    -0.07
    CCC
    -0.07
    239
    -0.07
    POSITIVE LOGITS
     respectively
    0.10
    isch
    0.09
    porto
    0.09
    sein
    0.08
     ï½Į
    0.08
    ench
    0.08
     Alv
    0.08
    orent
    0.08
    igham
    0.08
     Dy
    0.08
    Activations Density 0.138%

    No Known Activations