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. 19-RESID-POST-AA
    6. 127551
    Prev
    Next
    INDEX
    Explanations

    code or technical details

    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
     abych
    -0.07
    )();↵
    -0.06
    getConnection
    -0.06
    kemiz
    -0.06
     statement
    -0.06
    uards
    -0.06
    	before
    -0.06
     المل
    -0.06
     diy
    -0.06
    surname
    -0.05
    POSITIVE LOGITS
    _connections
    0.08
    operative
    0.07
     Colombia
    0.07
    datetime
    0.07
    426
    0.07
     Bone
    0.07
    "\↵
    0.07
     disadvantage
    0.07
     Colombian
    0.07
    -important
    0.07
    Activations Density 0.000%

    No Known Activations