Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 19-RESID-POST-AA
    6. 31526
    Prev
    Next
    INDEX
    Explanations

    Emma

    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
     Analog
    -0.07
     Koh
    -0.07
     lamin
    -0.06
     Ray
    -0.06
    Sele
    -0.06
    	bus
    -0.06
     orn
    -0.06
     cél
    -0.06
    ší
    -0.06
    "}}>↵
    -0.06
    POSITIVE LOGITS
    �示
    0.07
    ेदन
    0.07
    	true
    0.07
     Emma
    0.07
    emma
    0.07
    (chain
    0.07
     emot
    0.07
    IENCE
    0.06
    WARDED
    0.06
    ";"
    0.06
    Activations Density 0.001%

    No Known Activations