© 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. 57832
    Prev
    Next
    INDEX
    Explanations

    robots, work

    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
    _relative
    -0.07
     han
    -0.07
     Tango
    -0.07
    dere
    -0.07
                                 
    -0.06
    /ns
    -0.06
     бенз
    -0.06
     pong
    -0.06
     large
    -0.06
     پژ
    -0.06
    POSITIVE LOGITS
     TreeMap
    0.06
     каждый
    0.06
    Avatar
    0.06
    انات
    0.06
     الحي
    0.05
     의미
    0.05
    _GROUP
    0.05
    进一步
    0.05
    Transactions
    0.05
    ávací
    0.05
    Activations Density 0.039%

    No Known Activations