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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 3-RESID-POST-AA
    6. 122326
    Prev
    Next
    INDEX
    Explanations

    foreign characters

    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
     learner
    -0.07
    _MOBILE
    -0.06
    ρων
    -0.06
     dump
    -0.06
    naires
    -0.06
     stadium
    -0.06
    ))];↵
    -0.06
     tam
    -0.06
    _SU
    -0.06
    ]}</
    -0.06
    POSITIVE LOGITS
    스
    0.10
    프
    0.08
    드
    0.07
    플
    0.07
    크
    0.07
     링크
    0.07
     Алекс
    0.06
     �
    0.06
    .asp
    0.06
    τς
    0.06
    Activations Density 0.180%

    No Known Activations