© 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. 23442
    Prev
    Next
    INDEX
    Explanations

    body part suffixes and related contexts

    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
    edImage
    -0.12
     antlr
    -0.11
    odont
    -0.10
    ìľ¼ë¡ľ
    -0.10
    edback
    -0.10
    Ctrls
    -0.10
     pyl
    -0.09
    _PUSHDATA
    -0.09
    light
    -0.09
    eldo
    -0.09
    POSITIVE LOGITS
    gia
    0.18
    icious
    0.16
    ized
    0.16
    ization
    0.15
    loy
    0.15
     cavity
    0.15
    dehyde
    0.14
    izations
    0.14
    ike
    0.13
    ities
    0.12
    Activations Density 0.047%

    No Known Activations