© 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. 3-RESID-POST-AA
    6. 121464
    Prev
    Next
    INDEX
    Explanations

    structure/obstruction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .trigger
    -0.07
    _daily
    -0.06
    rací
    -0.06
     últimos
    -0.06
    .execSQL
    -0.06
    (Value
    -0.06
     nhập
    -0.06
     dipped
    -0.06
    Sw
    -0.06
     nied
    -0.06
    POSITIVE LOGITS
     obstruction
    0.10
     obstruct
    0.08
    struction
    0.06
    .Constraint
    0.06
    	Run
    0.06
    प
    0.06
    ональ
    0.06
    +</
    0.06
    _plugin
    0.06
    _tbl
    0.06
    Activations Density 0.004%

    No Known Activations