© 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. 25600
    Prev
    Next
    INDEX
    Explanations

    cause of undesirable outcomes

    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
    ä¹
    -0.09
    ï¾Ĩï¾Ĩ
    -0.09
    883
    -0.09
    문ìĿĦ
    -0.08
     Lanc
    -0.08
    ancellable
    -0.08
    igr
    -0.08
     Brend
    -0.08
    hani
    -0.08
    Łèĥ½
    -0.08
    POSITIVE LOGITS
     premature
    0.13
     overhe
    0.12
     scor
    0.12
     too
    0.12
     fou
    0.11
     oversh
    0.11
     Prem
    0.11
     losses
    0.10
     artifacts
    0.10
     loss
    0.10
    Activations Density 0.028%

    No Known Activations