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. 119636
    Prev
    Next
    INDEX
    Explanations

    to

    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
    純
    -0.07
    	code
    -0.07
    turnstile
    -0.06
     NGO
    -0.06
     judicial
    -0.06
     rebels
    -0.06
    /Gate
    -0.06
     EV
    -0.06
     Sé
    -0.06
     Bureau
    -0.06
    POSITIVE LOGITS
    ßerdem
    0.07
    命周期
    0.06
    己
    0.06
    	glColor
    0.06
    akukan
    0.06
    ินการ
    0.06
     Tag
    0.06
     любов
    0.06
     목소
    0.06
    (segment
    0.06
    Activations Density 0.174%

    No Known Activations