Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 53881
    Prev
    Next
    INDEX
    Explanations

    live

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ناحیه
    -0.07
     burst
    -0.07
    _yellow
    -0.06
    xb
    -0.06
     evident
    -0.06
     Bike
    -0.06
    �
    -0.06
     biri
    -0.06
     Dương
    -0.06
    Template
    -0.06
    POSITIVE LOGITS
     lived
    0.07
     ExecutionContext
    0.07
     Home
    0.07
     //////////////////
    0.06
     행복
    0.06
     foi
    0.06
     Charset
    0.06
    ользоват
    0.06
    "id
    0.06
    	async
    0.06
    Activations Density 0.018%

    No Known Activations