© 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. 77648
    Prev
    Next
    INDEX
    Explanations

    :

    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
    (cljs
    -0.07
    Episode
    -0.06
    clc
    -0.06
     cunning
    -0.06
     друго
    -0.06
    hf
    -0.06
    延
    -0.06
    avg
    -0.06
    .ST
    -0.06
     hos
    -0.06
    POSITIVE LOGITS
    ают
    0.07
     पहच
    0.06
    ované
    0.06
     brunette
    0.06
    /../
    0.06
    .preference
    0.06
     Invoice
    0.06
     weiß
    0.06
    .Identity
    0.06
    JR
    0.06
    Activations Density 0.009%

    No Known Activations