© 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. 19-RESID-POST-AA
    11. 54288
    Prev
    Next
    INDEX
    Explanations

    Medical risk/prevention

    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
    Properties
    -0.08
     데
    -0.07
     +=↵
    -0.07
    フ
    -0.07
     vitamins
    -0.07
    _TURN
    -0.06
    	service
    -0.06
    ुड
    -0.06
     nause
    -0.06
    ems
    -0.06
    POSITIVE LOGITS
     racket
    0.07
    ия
    0.06
     german
    0.06
    eyed
    0.06
    _repeat
    0.05
     youngster
    0.05
    ullet
    0.05
     wars
    0.05
    icopt
    0.05
    عدد
    0.05
    Activations Density 0.105%

    No Known Activations