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. 11-RESID-POST-AA
    6. 88479
    Prev
    Next
    INDEX
    Explanations

    ate

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    n
    -0.07
     Ji
    -0.07
    7
    -0.06
    Oh
    -0.06
     crucial
    -0.06
    Techn
    -0.06
    ,n
    -0.06
    111
    -0.06
    ,j
    -0.06
    11
    -0.06
    POSITIVE LOGITS
    ate
    0.16
    ATE
    0.13
    ات
    0.11
    ates
    0.11
    ulate
    0.10
    olate
    0.10
    agate
    0.10
    rate
    0.10
    iate
    0.09
    uate
    0.09
    Activations Density 0.040%

    No Known Activations