© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 37976
    Prev
    Next
    INDEX
    Explanations

    island of Hoy

    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
     seaside
    -0.12
     inland
    -0.11
     Coastal
    -0.10
     coastal
    -0.10
     Shore
    -0.10
     sever
    -0.09
     shoreline
    -0.09
     oceans
    -0.09
    IDES
    -0.09
    Snippet
    -0.08
    POSITIVE LOGITS
     island
    0.33
     islands
    0.30
     Island
    0.29
    å³¶
    0.27
    å²Ľ
    0.25
     оÑģÑĤÑĢов
    0.24
     Islands
    0.23
     جز
    0.19
    à¹Ģà¸ģาะ
    0.19
     Äijảo
    0.19
    Activations Density 0.044%

    No Known Activations