© 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. 27122
    Prev
    Next
    INDEX
    Explanations

    alike in form, sound, structure

    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
    <|begin_of_text|>
    -0.13
    è¨Ģèijī
    -0.13
     gramm
    -0.10
     omas
    -0.10
    jspx
    -0.09
     interp
    -0.09
     linguistic
    -0.09
     appe
    -0.09
     synt
    -0.09
    ump
    -0.08
    POSITIVE LOGITS
    izi
    0.11
     Tato
    0.10
     Particle
    0.09
    Modifiers
    0.09
    ozo
    0.09
     Compound
    0.09
    English
    0.09
    å°Ĭ
    0.08
     contexts
    0.08
     ⣨
    0.08
    Activations Density 0.005%

    No Known Activations