© 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. 44289
    Prev
    Next
    INDEX
    Explanations

    assistant : toxic : assign : 202

    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
     Lou
    -0.09
    tick
    -0.08
     Ler
    -0.08
    iker
    -0.08
    icker
    -0.08
    /an
    -0.08
    onta
    -0.08
     knee
    -0.08
     Vere
    -0.08
    agens
    -0.07
    POSITIVE LOGITS
     ç·
    0.11
    dek
    0.09
    <|end_header_id|>
    0.09
    asaki
    0.09
    __
    0.09
    liest
    0.08
    ship
    0.08
    .Formatter
    0.08
    xlim
    0.08
    ÚĨÙĩ
    0.08
    Activations Density 0.000%

    No Known Activations