© 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. 3-RESID-POST-AA
    11. 95268
    Prev
    Next
    INDEX
    Explanations

    div

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CoreApplication
    -0.06
    greg
    -0.06
    -score
    -0.06
    -sample
    -0.06
     �
    -0.06
    äche
    -0.06
     работы
    -0.06
    arma
    -0.06
    alph
    -0.06
    579
    -0.06
    POSITIVE LOGITS
     div
    0.28
    	div
    0.08
     rec
    0.07
    	cli
    0.06
     //#
    0.06
     '%"
    0.06
    認
    0.06
     DIV
    0.06
     personn
    0.06
     obr
    0.06
    Activations Density 0.003%

    No Known Activations