Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 128877
    Prev
    Next
    INDEX
    Explanations

    surrender

    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
    odie
    -0.07
    ísto
    -0.07
     DevExpress
    -0.06
    odic
    -0.06
    編
    -0.06
     ocas
    -0.06
     ">
    -0.06
     Probably
    -0.06
     read
    -0.06
     Js
    -0.06
    POSITIVE LOGITS
     surrender
    0.16
     surrendered
    0.16
     Surre
    0.08
     Sullivan
    0.07
    TRANSFER
    0.07
     relinqu
    0.07
     deliver
    0.07
     đảng
    0.07
     conquer
    0.07
    papers
    0.07
    Activations Density 0.003%

    No Known Activations