© 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. 121869
    Prev
    Next
    INDEX
    Explanations

    failure

    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
     obr
    -0.07
     pathology
    -0.07
    aceut
    -0.06
    "...
    -0.06
    Const
    -0.06
    	thread
    -0.06
     Stern
    -0.06
     TNT
    -0.06
     SPA
    -0.06
    .constant
    -0.05
    POSITIVE LOGITS
    �
    0.07
    saving
    0.07
     yakın
    0.06
    tableView
    0.06
     gcc
    0.06
    LOCK
    0.06
     currentUser
    0.06
     Elegant
    0.06
     {{{
    0.06
    009
    0.06
    Activations Density 0.008%

    No Known Activations