© 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. 15-RESID-POST-AA
    11. 105388
    Prev
    Next
    INDEX
    Explanations

    Code

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ético
    -0.07
     Mét
    -0.06
     associ
    -0.06
     BAL
    -0.06
     clar
    -0.06
    xeb
    -0.06
    Vy
    -0.06
     Contr
    -0.06
    ächst
    -0.06
    .•
    -0.06
    POSITIVE LOGITS
     QR
    0.06
    jm
    0.06
    _TOGGLE
    0.06
    .likes
    0.06
    	puts
    0.06
    >]
    0.06
    .Flag
    0.06
    ्मच
    0.06
     Nath
    0.06
    769
    0.06
    Activations Density 0.001%

    No Known Activations