© 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. 38066
    Prev
    Next
    INDEX
    Explanations

    Google’s policies and meta descriptions

    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
    agara
    -0.10
     Secrets
    -0.10
     sinc
    -0.09
    arity
    -0.09
     FI
    -0.09
     peer
    -0.09
     Peer
    -0.09
     saving
    -0.09
     IQ
    -0.09
     techno
    -0.09
    POSITIVE LOGITS
    SER
    0.17
     SER
    0.17
     Panda
    0.16
     Signals
    0.15
     signals
    0.15
     outr
    0.14
     authority
    0.14
    signals
    0.14
    Signals
    0.13
     Penguin
    0.13
    Activations Density 0.042%

    No Known Activations