© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44853
    Prev
    Next
    INDEX
    Explanations

    22 nucleotides

    np_max-act · gemini-2.0-flash

    terms related to cancer, particularly breast and lung cancer, including associated mechanisms and therapies.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects numeric measurements—especially counts, lengths, percentages, and approximate values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ruby
    -0.07
    ulses
    -0.06
    azo
    -0.06
     fullWidth
    -0.06
     geçir
    -0.06
    -floating
    -0.06
    osals
    -0.06
    loat
    -0.06
    bw
    -0.06
     Dun
    -0.06
    POSITIVE LOGITS
     веществ
    0.07
     (~(
    0.07
    (File
    0.07
    平成
    0.07
     %↵↵
    0.06
    .prepend
    0.06
    \\\
    0.06
     Singles
    0.06
    ื
    0.06
     chiếm
    0.06
    Activations Density 0.006%

    No Known Activations