© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 40418
    Prev
    Next
    INDEX
    Explanations

    rail

    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
    ()>
    -0.07
    �
    -0.07
     decomposition
    -0.07
     toen
    -0.07
    >m
    -0.06
     lady
    -0.06
     widow
    -0.06
    IVER
    -0.06
    }>
    -0.06
     kvinna
    -0.06
    POSITIVE LOGITS
     rail
    0.11
     Rail
    0.09
    Rail
    0.07
    ail
    0.07
     QMessageBox
    0.07
     Moh
    0.07
    air
    0.07
     rails
    0.07
     grassroots
    0.07
    ai
    0.06
    Activations Density 0.005%

    No Known Activations