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. 38352
    Prev
    Next
    INDEX
    Explanations

    abbreviations and acronyms

    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
     noreferrer
    -0.10
    ï½Ĭ
    -0.09
    /filepath
    -0.08
    EDGE
    -0.08
    rome
    -0.08
    IGH
    -0.08
    éĻ©
    -0.08
    æ¡£
    -0.08
    izon
    -0.08
     NSS
    -0.08
    POSITIVE LOGITS
     acronym
    0.11
     unp
    0.10
     NY
    0.10
     abbreviation
    0.09
    znik
    0.09
     bur
    0.09
    aaS
    0.09
    &S
    0.08
    ï½°
    0.08
    彡
    0.08
    Activations Density 0.192%

    No Known Activations