© 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. 7-RESID-POST-AA
    11. 27861
    Prev
    Next
    INDEX
    Explanations

    destructive

    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
    .blob
    -0.07
    개월
    -0.07
    igits
    -0.07
     Irving
    -0.06
     wang
    -0.06
    609
    -0.06
    �
    -0.06
    간
    -0.06
     idiot
    -0.06
     Malays
    -0.06
    POSITIVE LOGITS
     destructive
    0.14
     destruction
    0.10
    -destruct
    0.09
    destruct
    0.08
     destruct
    0.08
     Destruction
    0.08
    estruct
    0.08
     Consumption
    0.07
    ินทร
    0.07
    Для
    0.07
    Activations Density 0.003%

    No Known Activations