© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 94633
    Prev
    Next
    INDEX
    Explanations

    aging degradation

    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
    (write
    -0.07
     услов
    -0.07
     unos
    -0.07
     Obs
    -0.06
     gran
    -0.06
     일을
    -0.06
     kötü
    -0.06
    xad
    -0.06
     Sly
    -0.06
     유지
    -0.06
    POSITIVE LOGITS
     rámci
    0.06
    ку
    0.06
     lt
    0.06
     notices
    0.06
     au
    0.06
    getDoctrine
    0.06
     Prahy
    0.06
    кие
    0.06
    鉄
    0.06
     馬
    0.06
    Activations Density 0.028%

    No Known Activations