© 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. 41145
    Prev
    Next
    INDEX
    Explanations

    memory limit processing

    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
     丶
    -0.12
     mÃŃn
    -0.11
     SHARES
    -0.09
    _hz
    -0.09
     shelter
    -0.09
    áo
    -0.09
    leen
    -0.09
    slash
    -0.08
    elter
    -0.08
     ORM
    -0.08
    POSITIVE LOGITS
     memory
    0.13
     Memory
    0.12
     limit
    0.12
    è¶ħè¿ĩ
    0.12
     practical
    0.12
     è¶ħ
    0.11
     processing
    0.11
    Memory
    0.10
    memory
    0.10
     RAM
    0.10
    Activations Density 0.069%

    No Known Activations