© 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. 11-RESID-POST-AA
    11. 27418
    Prev
    Next
    INDEX
    Explanations

    Cortex

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -five
    -0.07
    Details
    -0.06
    USER
    -0.06
     Mariners
    -0.06
    蜜
    -0.06
     일부
    -0.06
    518
    -0.06
    553
    -0.06
    очь
    -0.06
     якості
    -0.06
    POSITIVE LOGITS
     Ryzen
    0.08
    izia
    0.07
    ampionship
    0.07
     Alex
    0.07
     행동
    0.07
    .ipv
    0.07
    onya
    0.07
    __((
    0.07
     pohled
    0.07
     Cory
    0.06
    Activations Density 0.000%

    No Known Activations