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. 15-RESID-POST-AA
    6. 4904
    Prev
    Next
    INDEX
    Explanations

    common English words

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    de
    -0.06
    部门
    -0.06
    abstractmethod
    -0.06
    rho
    -0.06
     여기
    -0.05
    展示
    -0.05
    -O
    -0.05
    整
    -0.05
    (member
    -0.05
     Wich
    -0.05
    POSITIVE LOGITS
     ripple
    0.07
    	Model
    0.07
    nung
    0.07
     star
    0.07
     giản
    0.07
     üret
    0.06
     Dro
    0.06
     Democratic
    0.06
    iterr
    0.06
    ibling
    0.06
    Activations Density 0.039%

    No Known Activations