© 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
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 44499
    Prev
    Next
    INDEX
    Explanations

    The following nouns

    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
     Glo
    -0.10
     ener
    -0.09
    afx
    -0.09
     ï½²
    -0.09
    ä»ģ
    -0.09
    quals
    -0.08
    ÐIJÑĢÑħÑĸв
    -0.08
     Lazar
    -0.08
     Flynn
    -0.08
     Affero
    -0.08
    POSITIVE LOGITS
     unders
    0.17
     parties
    0.16
     following
    0.15
    unders
    0.14
    following
    0.14
     provisions
    0.13
     Parties
    0.12
     seguint
    0.11
     sum
    0.11
     Following
    0.11
    Activations Density 0.080%

    No Known Activations