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. 5635
    Prev
    Next
    INDEX
    Explanations

    personal pronouns

    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
    _INSERT
    -0.07
    <Type
    -0.07
    SF
    -0.07
    OSP
    -0.07
     Suk
    -0.06
    _DICT
    -0.06
     цій
    -0.06
    .GONE
    -0.06
    _dicts
    -0.06
    OLUME
    -0.06
    POSITIVE LOGITS
     me
    0.09
     us
    0.08
     him
    0.06
    _bin
    0.06
     Exiting
    0.06
    OND
    0.06
    iyatı
    0.06
    جه
    0.06
    hone
    0.06
    Ly
    0.06
    Activations Density 0.066%

    No Known Activations