© 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. 44752
    Prev
    Next
    INDEX
    Explanations

    shortest path objective

    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
    -ln
    -0.11
    idot
    -0.10
    udson
    -0.10
     stale
    -0.09
     Hudson
    -0.09
     embargo
    -0.09
    eterminate
    -0.08
     Interr
    -0.08
     soap
    -0.08
    ached
    -0.08
    POSITIVE LOGITS
     binary
    0.16
     McCorm
    0.15
    .gdx
    0.14
     binaries
    0.14
    binary
    0.14
     Variables
    0.14
     variables
    0.13
     Binary
    0.13
    Binary
    0.13
     slack
    0.13
    Activations Density 0.010%

    No Known Activations