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. 125005
    Prev
    Next
    INDEX
    Explanations

    sign

    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
    “When
    -0.07
     MISSING
    -0.07
     AppComponent
    -0.07
    乐
    -0.07
     хорошо
    -0.07
     частини
    -0.07
     Liability
    -0.07
    恩
    -0.07
     گفت
    -0.06
    ENCE
    -0.06
    POSITIVE LOGITS
    folders
    0.06
    .Inter
    0.06
     wink
    0.06
    llum
    0.06
    Orden
    0.06
    '])
    0.06
     지금
    0.06
     newsp
    0.06
    titre
    0.06
     harass
    0.06
    Activations Density 0.037%

    No Known Activations