© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 2339
    Prev
    Next
    INDEX
    Explanations

    are able, was seen, and neglect

    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
     disappointing
    -0.11
    .scalablytyped
    -0.09
     caut
    -0.09
     earliest
    -0.09
    ÙħØ©
    -0.09
     incompetence
    -0.09
    λÏī
    -0.08
    æħİ
    -0.08
    .isOn
    -0.08
    .mybatis
    -0.08
    POSITIVE LOGITS
     wo
    0.16
    rush
    0.14
    缺
    0.14
     thiếu
    0.14
     lack
    0.13
     insufficient
    0.13
     poorly
    0.12
    ï¼Į没æľī
    0.12
     недоÑģÑĤаÑĤ
    0.12
     laisse
    0.12
    Activations Density 0.086%

    No Known Activations