© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 71781
    Prev
    Next
    INDEX
    Explanations

    pseudo

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Regulation
    -0.07
     yas
    -0.07
     bert
    -0.07
       
    -0.07
    _text
    -0.07
    \Php
    -0.07
    esda
    -0.06
    anni
    -0.06
     rating
    -0.06
     Maths
    -0.06
    POSITIVE LOGITS
    oire
    0.06
    ��
    0.06
     pasture
    0.06
     کند
    0.06
    >j
    0.06
    청
    0.06
     bogus
    0.06
    クラブ
    0.06
     portions
    0.06
    нам
    0.06
    Activations Density 0.004%

    No Known Activations