© 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. 118517
    Prev
    Next
    INDEX
    Explanations

    idea, invention

    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
    WHO
    -0.07
     evaluation
    -0.07
     завдання
    -0.06
    Gem
    -0.06
     drama
    -0.06
    	Collection
    -0.06
    .lab
    -0.06
     reconsider
    -0.06
    '),↵
    -0.06
    Tp
    -0.05
    POSITIVE LOGITS
    =f
    0.07
    šť
    0.07
     indoors
    0.07
    ucket
    0.07
    Ngoài
    0.07
    hl
    0.07
    ξύ
    0.06
    owied
    0.06
    τή
    0.06
    ={`${
    0.06
    Activations Density 0.101%

    No Known Activations