© 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
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 123172
    Prev
    Next
    INDEX
    Explanations

    donor

    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
     thi
    -0.07
     policemen
    -0.07
     коли
    -0.06
    玄
    -0.06
    íst
    -0.06
    Verse
    -0.06
     пару
    -0.06
     알고
    -0.06
     रन
    -0.06
    еди
    -0.06
    POSITIVE LOGITS
     donor
    0.17
     donors
    0.16
    (Source
    0.07
     Clients
    0.06
    ��
    0.06
     disqualified
    0.06
    buie
    0.06
    or
    0.06
     Blazers
    0.06
     dengan
    0.06
    Activations Density 0.002%

    No Known Activations