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. 44967
    Prev
    Next
    INDEX
    Explanations

    ... give me bots

    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
     -*-č\n
    -0.09
    ¦æĥħ
    -0.08
    ToolStripMenuItem
    -0.08
    InChildren
    -0.07
    FromClass
    -0.07
    _embed
    -0.07
    \Bridge
    -0.07
    _shortcode
    -0.07
    wan
    -0.07
    AtPath
    -0.06
    POSITIVE LOGITS
    ...
    0.08
    ...\n
    0.08
     Whites
    0.07
    íĨłíĨł
    0.07
     abs
    0.07
    akens
    0.07
    cont
    0.06
     _
    0.06
     chuck
    0.06
    ÐIJÑĢÑħÑĸв
    0.06
    Activations Density 1.128%

    No Known Activations