© 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. 34601
    Prev
    Next
    INDEX
    Explanations

    naming and description

    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
     correctness
    -0.09
    okable
    -0.09
     '\''
    -0.09
    redirectTo
    -0.09
     correct
    -0.09
     doÄŁru
    -0.09
     Vert
    -0.09
     Cow
    -0.08
    conte
    -0.08
    gnu
    -0.08
    POSITIVE LOGITS
     appropriate
    0.17
     unique
    0.17
     suitable
    0.17
     meaningful
    0.16
    éģ©
    0.16
    unique
    0.15
    ä»»
    0.14
     arbit
    0.14
     desired
    0.13
    appropriate
    0.13
    Activations Density 0.108%

    No Known Activations