© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 53914
    Prev
    Next
    INDEX
    Explanations

    target

    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
     $('<
    -0.07
     evapor
    -0.07
     wakes
    -0.07
    mAh
    -0.07
    .FragmentManager
    -0.06
     계
    -0.06
     hizo
    -0.06
     rinse
    -0.06
     выс
    -0.06
     徒歩
    -0.06
    POSITIVE LOGITS
     targeting
    0.13
     targeted
    0.11
     targets
    0.09
     vicious
    0.07
     target
    0.07
    Target
    0.07
     polov
    0.07
     Target
    0.06
     dubbed
    0.06
     Targets
    0.06
    Activations Density 0.015%

    No Known Activations