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. 45012
    Prev
    Next
    INDEX
    Explanations

    crucial management of behavior, tinnitus, skin, history, skills

    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
    elage
    -0.09
    ukkan
    -0.09
    umm
    -0.09
    ings
    -0.09
    ellation
    -0.08
    atis
    -0.08
    :Register
    -0.08
     Vz
    -0.08
    OrNull
    -0.08
     Kum
    -0.08
    POSITIVE LOGITS
     essential
    0.20
     Cruc
    0.17
     plays
    0.17
     crucial
    0.15
     vital
    0.15
    essential
    0.15
     cruc
    0.14
     absolutely
    0.13
     Essential
    0.13
     critical
    0.13
    Activations Density 0.085%

    No Known Activations