© 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
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 95458
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    entes
    -0.06
     Cult
    -0.06
    :{
    ↵
    -0.06
    раз
    -0.06
     Grow
    -0.06
    anky
    -0.06
    awner
    -0.06
     science
    -0.06
    ротив
    -0.06
    apture
    -0.06
    POSITIVE LOGITS
     domácí
    0.06
     Alert
    0.06
     Walton
    0.06
    	glBind
    0.06
    _ACT
    0.06
     İn
    0.06
     Approx
    0.06
    %E
    0.06
    альну
    0.06
    _EVENTS
    0.06
    Activations Density 0.240%

    No Known Activations