© 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. 29029
    Prev
    Next
    INDEX
    Explanations

    overactive or abnormal states

    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
     ret
    -0.10
     fuzz
    -0.09
    ält
    -0.09
     discontin
    -0.09
     Belle
    -0.09
     neglected
    -0.08
    laz
    -0.08
     infr
    -0.08
    cil
    -0.08
     Transcript
    -0.08
    POSITIVE LOGITS
     abnormal
    0.21
     excess
    0.19
     Hyper
    0.15
     ab
    0.14
     hyper
    0.14
    Hyper
    0.14
    hyper
    0.14
     normals
    0.13
     excessive
    0.13
    normal
    0.13
    Activations Density 0.086%

    No Known Activations