© 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. 97857
    Prev
    Next
    INDEX
    Explanations

    customer reviews

    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
     infiltration
    -0.07
    发行
    -0.07
     드립니다
    -0.06
     чувств
    -0.06
    immers
    -0.06
     Registro
    -0.06
    анных
    -0.06
    yyyyMMdd
    -0.06
     knowingly
    -0.06
    鸟
    -0.06
    POSITIVE LOGITS
     follower
    0.07
    das
    0.07
     sights
    0.07
     him
    0.06
    ことで
    0.06
    ']
↵
    0.06
     retaining
    0.06
     والأ
    0.06
    _admin
    0.06
    afort
    0.06
    Activations Density 0.013%

    No Known Activations