© 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. 38667
    Prev
    Next
    INDEX
    Explanations

    often followed by verbs, to followed by verbs

    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
    ¶Į
    -0.17
    ÂĢÂĢ
    -0.14
    łéĻ¤
    -0.12
    ¦æĥħ
    -0.12
    įng
    -0.12
     -*-č\n
    -0.12
    ¨ë¶Ģ
    -0.11
    ¡´
    -0.11
    ³ç´°
    -0.10
    opak
    -0.09
    POSITIVE LOGITS
    'gc
    0.08
     :\n\n
    0.08
     G
    0.08
     :\n
    0.08
    ÂŃ
    0.08
     topo
    0.08
     Read
    0.08
     MAS
    0.08
     T
    0.08
    :\n\n
    0.07
    Activations Density 0.493%

    No Known Activations