Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 65038
    Prev
    Next
    INDEX
    Explanations

    word followed by specific continuation

    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
    łéϤ
    -0.12
    ¶Į
    -0.11
    ¦æĥħ
    -0.10
    ÂĢÂĢ
    -0.10
    ³ç´°
    -0.10
    ******č\n
    -0.10
    .Formatter
    -0.09
    ÐIJÑĢÑħÑĸв
    -0.09
    įng
    -0.09
    ķãĤĵ
    -0.09
    POSITIVE LOGITS
     overall
    0.12
    overall
    0.10
     future
    0.09
     Overall
    0.09
    future
    0.09
     ultimately
    0.08
    Overall
    0.08
    à¸Ļà¸Ń
    0.08
    malink
    0.07
    "./
    0.07
    Activations Density 0.602%

    No Known Activations