© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 33234
    Prev
    Next
    INDEX
    Explanations

    belief in, different from, way of

    np_acts-logits-general · gemini-2.5-flash-lite

    definitional or explanatory clauses that describe what something is or means.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @yooniel31
    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
     fucking
    -0.10
     Fucking
    -0.10
     amat
    -0.10
     FUCK
    -0.10
     embar
    -0.10
    Ìģ
    -0.10
     ​​​
    -0.09
     suce
    -0.09
     limitless
    -0.09
    arak
    -0.09
    POSITIVE LOGITS
     dat
    0.18
    dat
    0.14
    个
    0.14
     folks
    0.13
     dere
    0.13
    akin
    0.13
    perty
    0.13
     ol
    0.13
    å¼Ĺ
    0.12
     uv
    0.12
    Activations Density 0.179%

    No Known Activations