© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 114012
    Prev
    Next
    INDEX
    Explanations

    avoid

    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
    metal
    -0.07
    aku
    -0.07
    aker
    -0.06
     Apt
    -0.06
    -handler
    -0.06
    hma
    -0.06
    .sam
    -0.06
     StyleSheet
    -0.06
     dolaş
    -0.06
    reamble
    -0.06
    POSITIVE LOGITS
     implicitly
    0.08
    >f
    0.07
    ασία
    0.07
    이지
    0.07
    -registration
    0.06
    mination
    0.06
    รง
    0.06
    olynomial
    0.06
    ULO
    0.06
     hashed
    0.06
    Activations Density 0.000%

    No Known Activations