© 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. 109007
    Prev
    Next
    INDEX
    Explanations

    tar archives

    np_max-act · gemini-2.0-flash

    The neuron flags tokens involved in software release/download metadata—archive filenames (e.g. “.tar”, “.gz”, “.bz2”, “.xz”) and checksum labels (e.g. “sha1”, “md5”, “sha256”).

    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
    Exit
    -0.06
    pas
    -0.06
    _prev
    -0.06
    Quarter
    -0.06
    goo
    -0.06
    Mask
    -0.06
    _tag
    -0.06
    .sendMessage
    -0.06
    Kom
    -0.06
    Ya
    -0.05
    POSITIVE LOGITS
     Tòa
    0.08
     глав
    0.07
    'order
    0.07
     Dwarf
    0.07
     privile
    0.07
    thern
    0.06
     первой
    0.06
     midi
    0.06
    rowse
    0.06
     Korea
    0.06
    Activations Density 0.004%

    No Known Activations