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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 15-RESID-POST-AA
    6. 30821
    Prev
    Next
    INDEX
    Explanations

    scientific/technical writing

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -mouth
    -0.07
    통
    -0.07
     NAME
    -0.06
    imenti
    -0.06
    ensch
    -0.06
     acidic
    -0.06
     petites
    -0.06
    เฟ
    -0.06
    램
    -0.06
    _schema
    -0.06
    POSITIVE LOGITS
    (parts
    0.06
    jmp
    0.06
    (server
    0.06
    reglo
    0.06
    	b
    0.06
     مهندسی
    0.06
    HK
    0.06
     адрес
    0.06
     Luật
    0.06
     hareket
    0.06
    Activations Density 0.000%

    No Known Activations