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. 7-RESID-POST-AA
    6. 39473
    Prev
    Next
    INDEX
    Explanations

    organizations and clubs

    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
    .iv
    -0.07
     spirit
    -0.07
    ेव
    -0.06
    _many
    -0.06
    appid
    -0.06
    false
    -0.06
    Snap
    -0.06
    Start
    -0.06
    .Dictionary
    -0.06
    それ
    -0.06
    POSITIVE LOGITS
     نتیجه
    0.07
    ře
    0.07
     pagina
    0.07
     chapter
    0.06
    ุป
    0.06
    专业
    0.06
     інформа
    0.06
    .LE
    0.06
     reminiscent
    0.06
           
    0.06
    Activations Density 0.151%

    No Known Activations