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. 65189
    Prev
    Next
    INDEX
    Explanations

    taking into account

    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
    seealso
    -0.09
     Leonard
    -0.09
     lineup
    -0.09
     Jarvis
    -0.09
     Laud
    -0.08
     sal
    -0.08
    곡
    -0.08
    adan
    -0.08
     Carlton
    -0.08
    vetica
    -0.08
    POSITIVE LOGITS
     account
    0.39
     Account
    0.28
    account
    0.27
     cuenta
    0.26
     compte
    0.25
     consideration
    0.25
    Account
    0.23
    -account
    0.22
    _account
    0.22
     mind
    0.21
    Activations Density 0.015%

    No Known Activations