© 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. 19-RESID-POST-AA
    6. 29403
    Prev
    Next
    INDEX
    Explanations

    the

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NGC
    -0.06
     할인
    -0.06
     grown
    -0.06
    �
    -0.06
    (a
    -0.06
    _TOGGLE
    -0.06
    (keys
    -0.06
    	IN
    -0.06
     Msg
    -0.05
    yll
    -0.05
    POSITIVE LOGITS
     UIAlertView
    0.06
     влас
    0.06
    융
    0.06
    UIAlertView
    0.06
    WW
    0.06
    nav
    0.06
    ционного
    0.06
     Synd
    0.06
     Karnataka
    0.06
     rencontres
    0.06
    Activations Density 0.011%

    No Known Activations