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. 93610
    Prev
    Next
    INDEX
    Explanations

    remote control systems

    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
    责任
    -0.07
    .Rec
    -0.07
     hormones
    -0.06
    치
    -0.06
     dru
    -0.06
    разу
    -0.06
    _bar
    -0.06
     Expansion
    -0.06
    _ZONE
    -0.06
    Do
    -0.06
    POSITIVE LOGITS
     mình
    0.07
     Pratt
    0.06
    erset
    0.06
    517
    0.06
    �
    0.06
     Xuân
    0.06
    (conn
    0.06
    submit
    0.06
     vacuum
    0.06
    _less
    0.06
    Activations Density 0.117%

    No Known Activations