© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 121772
    Prev
    Next
    INDEX
    Explanations

    user

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    590
    -0.07
     moveTo
    -0.07
    (completion
    -0.06
    loadModel
    -0.06
     nouvelle
    -0.06
    =logging
    -0.06
     lcm
    -0.06
     bolt
    -0.06
     finite
    -0.06
    _fetch
    -0.06
    POSITIVE LOGITS
     User
    0.17
     user
    0.16
    User
    0.16
    _user
    0.14
    	user
    0.13
     users
    0.13
    user
    0.12
    _USER
    0.12
     Users
    0.12
    .user
    0.12
    Activations Density 0.335%

    No Known Activations