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. 19-RESID-POST-AA
    6. 30901
    Prev
    Next
    INDEX
    Explanations

    to

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     restraining
    -0.06
    _stuff
    -0.06
     rằng
    -0.05
     marginTop
    -0.05
     Dut
    -0.05
     Рос
    -0.05
    era
    -0.05
    พย
    -0.05
     ($("#
    -0.05
     kriz
    -0.05
    POSITIVE LOGITS
    ,r
    0.07
    .Auto
    0.07
    \Models
    0.07
     distant
    0.07
     ensuring
    0.07
     ViewPager
    0.06
     Ré
    0.06
     Firstly
    0.06
     Citizen
    0.06
     Imp
    0.06
    Activations Density 0.001%

    No Known Activations