© 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. 7-RESID-POST-AA
    11. 112203
    Prev
    Next
    INDEX
    Explanations

    deeper

    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
     Lives
    -0.06
    睡
    -0.06
    opro
    -0.06
     thiểu
    -0.06
    шего
    -0.06
    观看
    -0.06
     bipartisan
    -0.06
    locator
    -0.06
    redo
    -0.06
    投
    -0.06
    POSITIVE LOGITS
     indentation
    0.08
    Exposed
    0.07
    >false
    0.07
     числа
    0.06
    ạo
    0.06
     Powerful
    0.06
    .onPause
    0.06
    boxes
    0.06
    (pub
    0.06
    	explicit
    0.06
    Activations Density 0.009%

    No Known Activations