© 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. 34674
    Prev
    Next
    INDEX
    Explanations

    mate

    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
     hugely
    -0.11
    butt
    -0.10
     ãĥ¾
    -0.09
     Butt
    -0.09
     negro
    -0.09
     Rider
    -0.09
    å£
    -0.09
    fts
    -0.09
    elves
    -0.09
    ÌĤ
    -0.09
    POSITIVE LOGITS
     mate
    0.20
     mates
    0.20
     blo
    0.19
    Oi
    0.18
     proper
    0.16
     bits
    0.15
     brill
    0.15
    mate
    0.15
     Mate
    0.14
    mates
    0.14
    Activations Density 0.092%

    No Known Activations