© 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
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 34505
    Prev
    Next
    INDEX
    Explanations

    end of text to assistant header

    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
    ages
    -0.09
    YRO
    -0.09
    bsolute
    -0.09
     pand
    -0.09
    ister
    -0.09
     Pand
    -0.09
    otta
    -0.08
     bib
    -0.08
     Rac
    -0.08
     Cher
    -0.08
    POSITIVE LOGITS
    å½»
    0.10
     rele
    0.09
    <|begin_of_text|>
    0.09
     Shim
    0.08
     Herz
    0.08
    nofollow
    0.08
    oplevel
    0.08
    ANS
    0.08
     Spike
    0.08
     Wich
    0.08
    Activations Density 0.054%

    No Known Activations