© 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. 7658
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    This neuron primarily detects host‐and‐port patterns (e.g. IP addresses or hostnames followed by “:port”).

    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
     แบบ
    -0.08
    Tau
    -0.07
    Books
    -0.06
    اشت
    -0.06
    itin
    -0.06
    LatLng
    -0.06
    InputModule
    -0.06
    getline
    -0.06
    vek
    -0.06
    -columns
    -0.06
    POSITIVE LOGITS
     proporcion
    0.07
    γνω
    0.06
     pornofil
    0.06
     σχέ
    0.06
     sophisticated
    0.06
    締
    0.06
     ethn
    0.06
     Troy
    0.06
     republic
    0.06
     reimbursement
    0.06
    Activations Density 0.004%

    No Known Activations