© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 34953
    Prev
    Next
    INDEX
    Explanations

    offering assistance or help

    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
    ipped
    -0.08
     reve
    -0.08
    enef
    -0.08
    ï¼¹
    -0.08
    OLS
    -0.08
     Caroline
    -0.08
    vero
    -0.08
    obao
    -0.08
    íĥģ
    -0.08
     Swarm
    -0.08
    POSITIVE LOGITS
    chat
    0.12
     chat
    0.10
    24
    0.09
    éĹ²
    0.09
     Mon
    0.09
    Ñīа
    0.09
    å°½
    0.09
     answer
    0.09
    .ss
    0.08
     Entertainment
    0.08
    Activations Density 0.044%

    No Known Activations