© 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
    5. 50-RESID-POST-GF
    7. 33906
    Prev
    Next
    INDEX
    Explanations

    ors

    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
    iese
    -0.10
    ately
    -0.10
    zet
    -0.10
    ood
    -0.09
    awl
    -0.09
    oose
    -0.09
    aby
    -0.09
    ly
    -0.09
    ROP
    -0.09
    ERM
    -0.09
    POSITIVE LOGITS
    ors
    0.37
    åĻ¨
    0.24
    ores
    0.24
    ORS
    0.23
    urs
    0.21
    eur
    0.21
    ored
    0.20
    tor
    0.20
    èĢħ
    0.20
    iors
    0.19
    Activations Density 0.081%

    No Known Activations