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. 7-RESID-POST-AA
    6. 111626
    Prev
    Next
    INDEX
    Explanations

    taxable

    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
    igsaw
    -0.07
    _eta
    -0.06
     우
    -0.06
    ت
    -0.06
    産
    -0.06
     سازی
    -0.06
    FORM
    -0.06
    ану
    -0.06
    まる
    -0.06
     グ
    -0.06
    POSITIVE LOGITS
     taxable
    0.13
     Joker
    0.07
     Snapchat
    0.06
    	canvas
    0.06
    declar
    0.06
    array
    0.06
     pathway
    0.06
    ezpe
    0.06
     breast
    0.06
     Wiley
    0.06
    Activations Density 0.000%

    No Known Activations