© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 58573
    Prev
    Next
    INDEX
    Explanations

    house

    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
     buildings
    -0.11
     Buildings
    -0.10
    atz
    -0.10
    æŁľ
    -0.09
     expend
    -0.09
    ombre
    -0.09
    homes
    -0.09
     cott
    -0.09
    /UI
    -0.08
    APTER
    -0.08
    POSITIVE LOGITS
    opathic
    0.14
    nette
    0.14
     пÑĢеÑģÑĤ
    0.14
    /ap
    0.12
    guest
    0.12
    ickness
    0.12
    keeping
    0.12
    乡
    0.11
     pref
    0.11
    wares
    0.11
    Activations Density 0.040%

    No Known Activations