© 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. 44522
    Prev
    Next
    INDEX
    Explanations

    top left positions

    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
     Tops
    -0.10
    emes
    -0.09
    -toggler
    -0.09
    angl
    -0.09
    626
    -0.09
    jie
    -0.09
    ascript
    -0.08
    AXB
    -0.08
    .eulerAngles
    -0.08
    RefCount
    -0.08
    POSITIVE LOGITS
     left
    0.22
     far
    0.20
     middle
    0.18
     right
    0.16
    å·¦
    0.16
     center
    0.16
     extreme
    0.15
    åı³
    0.14
    left
    0.13
    è¿ľ
    0.13
    Activations Density 0.055%

    No Known Activations