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. 3-RESID-POST-AA
    6. 122940
    Prev
    Next
    INDEX
    Explanations

    let

    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
    []=
    -0.07
    >k
    -0.06
    inux
    -0.06
     hose
    -0.06
     interpersonal
    -0.06
     TextFormField
    -0.06
     enfrent
    -0.06
     Bayer
    -0.06
     nose
    -0.06
     ι
    -0.06
    POSITIVE LOGITS
    let
    0.40
    lets
    0.30
    LET
    0.30
    lett
    0.21
    лет
    0.17
    leta
    0.14
    	let
    0.14
    lete
    0.13
    leted
    0.13
     let
    0.13
    Activations Density 0.015%

    No Known Activations