© 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. 37885
    Prev
    Next
    INDEX
    Explanations

    a noun

    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
     hob
    -0.10
     Hob
    -0.10
     coll
    -0.10
    irs
    -0.09
     pa
    -0.09
     ch
    -0.09
    krom
    -0.09
     en
    -0.09
    æĵ
    -0.09
    arem
    -0.08
    POSITIVE LOGITS
     range
    0.16
     series
    0.16
     policy
    0.15
     number
    0.15
     serie
    0.14
    policy
    0.12
     variety
    0.12
    series
    0.12
     philosophy
    0.11
     ÅĻada
    0.11
    Activations Density 0.009%

    No Known Activations