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. 36190
    Prev
    Next
    INDEX
    Explanations

    Dismissal of serious issues

    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
     QUEUE
    -0.07
     sync
    -0.06
     disadvantages
    -0.06
     ngân
    -0.06
     лиц
    -0.06
     біблі
    -0.06
     душ
    -0.06
     save
    -0.06
    _attack
    -0.06
     망
    -0.06
    POSITIVE LOGITS
    @Autowired
    0.07
    Override
    0.07
     Prior
    0.06
    .body
    0.06
    batis
    0.06
     fut
    0.06
    (Property
    0.06
    .addTab
    0.06
     oci
    0.06
     тобі
    0.06
    Activations Density 0.146%

    No Known Activations