© 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. 19-RESID-POST-AA
    11. 28197
    Prev
    Next
    INDEX
    Explanations

    halo, ali

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     δημιουργ
    -0.07
    帝
    -0.06
     ar
    -0.06
     Advisors
    -0.06
     Sat
    -0.06
     empir
    -0.06
     опыт
    -0.06
    ive
    -0.06
     tad
    -0.06
    왔
    -0.06
    POSITIVE LOGITS
     Instances
    0.07
    /></
    0.07
    hall
    0.07
     schvál
    0.07
    _Close
    0.07
    _DU
    0.06
    čních
    0.06
    hal
    0.06
    TC
    0.06
     threading
    0.06
    Activations Density 0.018%

    No Known Activations