© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 25214
    Prev
    Next
    INDEX
    Explanations

    -w

    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
     Plaza
    -0.08
    .channel
    -0.06
    .DESC
    -0.06
    quiv
    -0.06
    .getServer
    -0.06
     Hu
    -0.06
     kötü
    -0.06
     Latino
    -0.06
     Flying
    -0.06
    .:.:.:.:
    -0.06
    POSITIVE LOGITS
    -a
    0.07
     mornings
    0.06
    매
    0.06
    -s
    0.06
    अ
    0.06
    -t
    0.06
    -N
    0.06
    念
    0.06
     Cheap
    0.06
     محمد
    0.06
    Activations Density 0.025%

    No Known Activations