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. 15-RESID-POST-AA
    6. 75175
    Prev
    Next
    INDEX
    Explanations

    should

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ्वर
    -0.07
    Ó
    -0.07
    chwitz
    -0.07
    aturdays
    -0.07
     multin
    -0.07
     wizards
    -0.07
    32
    -0.06
    mania
    -0.06
     VLAN
    -0.06
    22
    -0.06
    POSITIVE LOGITS
     should
    0.18
    should
    0.16
     Should
    0.14
    Should
    0.13
     SHOULD
    0.12
     shouldn
    0.11
    .should
    0.08
    应当
    0.08
    _should
    0.08
     suggests
    0.08
    Activations Density 0.069%

    No Known Activations