© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 11690
    Prev
    Next
    INDEX
    Explanations

    valid: hashable, any type, square

    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
     unus
    -0.11
    usable
    -0.10
    hue
    -0.09
    liable
    -0.09
     configurable
    -0.09
     pne
    -0.08
    lla
    -0.08
     Harr
    -0.08
     blockIdx
    -0.08
    razy
    -0.08
    POSITIVE LOGITS
     valid
    0.18
    valid
    0.14
     legal
    0.14
     supported
    0.14
     VALID
    0.13
    _valid
    0.13
    -valid
    0.12
    Valid
    0.12
     Valid
    0.12
     compatible
    0.12
    Activations Density 0.116%

    No Known Activations