© 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
    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. 27578
    Prev
    Next
    INDEX
    Explanations

    actions

    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
     Better
    -0.06
    电影
    -0.06
     Truly
    -0.06
     TMZ
    -0.06
    Как
    -0.06
    Ц
    -0.06
     موس
    -0.06
    око
    -0.06
    оном
    -0.06
     newArray
    -0.06
    POSITIVE LOGITS
    AVE
    0.07
    HECK
    0.07
    ibia
    0.07
     initView
    0.07
    Thinking
    0.06
    member
    0.06
    ARN
    0.06
    IKE
    0.06
    uft
    0.06
     Platforms
    0.06
    Activations Density 0.065%

    No Known Activations