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. 128748
    Prev
    Next
    INDEX
    Explanations

    ics

    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
    forced
    -0.07
    芝
    -0.06
     getToken
    -0.06
    _Row
    -0.06
    arging
    -0.06
    、_
    -0.06
     Thánh
    -0.06
     yên
    -0.06
    다
    -0.06
     تحت
    -0.06
    POSITIVE LOGITS
     charisma
    0.07
    visející
    0.07
       
    0.07
     nums
    0.06
     experimented
    0.06
    如果
    0.06
    >>,
    0.06
    ]init
    0.06
     telecommunications
    0.06
     migrating
    0.06
    Activations Density 0.013%

    No Known Activations