© 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. 60323
    Prev
    Next
    INDEX
    Explanations

    inv prefix with common continuations

    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
    alc
    -0.10
    unc
    -0.10
    èĤ
    -0.10
    icult
    -0.09
    ald
    -0.09
     vag
    -0.09
    opr
    -0.09
     Wilde
    -0.08
    IDES
    -0.08
    edenÃŃ
    -0.08
    POSITIVE LOGITS
     inv
    0.17
    TargetException
    0.17
    (inv
    0.14
    olved
    0.14
    .Inv
    0.13
    .inv
    0.13
     INV
    0.13
     Inv
    0.12
    inv
    0.12
    olve
    0.12
    Activations Density 0.022%

    No Known Activations