© 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
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 84681
    Prev
    Next
    INDEX
    Explanations

    toc

    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
    대로
    -0.07
     �
    -0.07
    龍
    -0.06
     respectively
    -0.06
    pictured
    -0.06
    Prot
    -0.06
    curacy
    -0.06
     demonstrated
    -0.06
    喔
    -0.06
     isEmpty
    -0.06
    POSITIVE LOGITS
    読
    0.07
    (handle
    0.07
     parch
    0.07
     شناس
    0.07
     hormonal
    0.06
    -gnu
    0.06
    clare
    0.06
     발
    0.06
    _GO
    0.06
     �
    0.06
    Activations Density 0.001%

    No Known Activations