© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 60515
    Prev
    Next
    INDEX
    Explanations

    prefix actions or states

    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
    ','','
    -0.09
     Rog
    -0.09
     Garrett
    -0.09
    /'.$
    -0.09
    (\$
    -0.09
    ÑģÑĤÑĢÑĥ
    -0.09
    arcy
    -0.09
     Roo
    -0.09
    oloj
    -0.09
     \/
    -0.08
    POSITIVE LOGITS
     prefix
    0.14
    ¯u
    0.11
     Prefix
    0.10
    Prefix
    0.10
     prefixes
    0.09
     Watkins
    0.09
     Grimm
    0.09
     '",
    0.08
     Quiz
    0.08
    _prefix
    0.08
    Activations Density 0.115%

    No Known Activations