© 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
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 25437
    Prev
    Next
    INDEX
    Explanations

    drug

    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
    äche
    -0.07
    итуа
    -0.07
    adius
    -0.07
    embali
    -0.07
     města
    -0.07
    pection
    -0.07
    颜
    -0.07
     Maven
    -0.07
    iam
    -0.06
    _CENTER
    -0.06
    POSITIVE LOGITS
     drugs
    0.09
     drug
    0.08
     Drug
    0.08
    (gr
    0.07
    (inp
    0.07
    (nextProps
    0.07
    (q
    0.07
     Gran
    0.06
     Explicit
    0.06
     нар
    0.06
    Activations Density 0.018%

    No Known Activations