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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 58000
    Prev
    Next
    INDEX
    Explanations

    head

    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
     우리는
    -0.07
    ụy
    -0.06
     dříve
    -0.06
     Vincent
    -0.06
    _categoria
    -0.06
    �
    -0.06
    iro
    -0.06
     Riley
    -0.06
     rent
    -0.06
    ią
    -0.06
    POSITIVE LOGITS
     head
    0.21
     Head
    0.19
    head
    0.18
     heads
    0.17
    Head
    0.16
     HEAD
    0.16
    HEAD
    0.15
    -head
    0.14
     Heads
    0.13
    heads
    0.13
    Activations Density 0.033%

    No Known Activations