© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54323
    Prev
    Next
    INDEX
    Explanations

    blob

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the word “blob” (e.g. Azure Blob storage API references).

    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
     enthusiast
    -0.07
    Mount
    -0.07
    endir
    -0.07
    _Vert
    -0.07
    quote
    -0.07
    Activity
    -0.07
    xfe
    -0.07
    achte
    -0.06
     $#
    -0.06
     Seven
    -0.06
    POSITIVE LOGITS
     Blob
    0.09
    (blob
    0.09
    Blob
    0.09
     blobs
    0.09
     blob
    0.08
    ib
    0.08
    IB
    0.08
     Blo
    0.07
    hib
    0.07
     bids
    0.07
    Activations Density 0.002%

    No Known Activations