© 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
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 99228
    Prev
    Next
    INDEX
    Explanations

    clude

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hammer
    -0.07
    ]<<"
    -0.07
     inhibitors
    -0.06
     Morrison
    -0.06
     myster
    -0.06
    IfNeeded
    -0.06
     surgery
    -0.06
    やす
    -0.06
    扶
    -0.06
     أف
    -0.06
    POSITIVE LOGITS
    clude
    0.08
    CLUDING
    0.07
    �
    0.07
    Coding
    0.07
     Reliable
    0.07
    cluded
    0.06
     graceful
    0.06
    cribed
    0.06
    ά
    0.06
    croll
    0.06
    Activations Density 0.002%

    No Known Activations