© 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. 19-RESID-POST-AA
    11. 111800
    Prev
    Next
    INDEX
    Explanations

    negative self-perception

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ACK
    -0.07
    �
    -0.06
     outspoken
    -0.06
     zřejmě
    -0.06
    itsu
    -0.06
    Al
    -0.06
     jaar
    -0.06
     destruction
    -0.06
     इ
    -0.06
     gib
    -0.06
    POSITIVE LOGITS
     сбор
    0.07
    Impact
    0.07
     stom
    0.07
    责
    0.06
    .running
    0.06
     misconception
    0.06
     investigations
    0.06
     thu
    0.06
    Theory
    0.06
     θα
    0.06
    Activations Density 0.062%

    No Known Activations