© 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. 120895
    Prev
    Next
    INDEX
    Explanations

    Academic/technical writing from Taiwan

    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
    악
    -0.06
    erializer
    -0.06
    .es
    -0.06
     엄마
    -0.06
    .auto
    -0.06
     pantalla
    -0.06
    nar
    -0.06
    -अ
    -0.06
    _codec
    -0.06
    -host
    -0.06
    POSITIVE LOGITS
     Taipei
    0.07
    亿元
    0.07
     recognizer
    0.07
    BindView
    0.07
     Cheryl
    0.06
     δο
    0.06
     redesigned
    0.06
     compressor
    0.06
    ickt
    0.06
     Nẵng
    0.06
    Activations Density 0.046%

    No Known Activations