Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 83686
    Prev
    Next
    INDEX
    Explanations

    locations and communities

    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
    -comm
    -0.07
    -directory
    -0.06
     Weapon
    -0.06
     which
    -0.06
    (par
    -0.06
     complicated
    -0.06
     municip
    -0.06
    Brightness
    -0.06
    .raise
    -0.06
    Show
    -0.06
    POSITIVE LOGITS
    pd
    0.06
    EL
    0.06
    IG
    0.06
    алу
    0.06
    onna
    0.06
     nev
    0.06
    .Tag
    0.06
    zent
    0.06
    şk
    0.06
    łem
    0.05
    Activations Density 0.083%

    No Known Activations