© 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. 11-RESID-POST-AA
    11. 110213
    Prev
    Next
    INDEX
    Explanations

    ters

    np_max-act · gemini-2.0-flash

    the presence of animal names or species references.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    //{{
    -0.06
     Ocean
    -0.06
    	short
    -0.06
     ",";↵
    -0.06
     Gran
    -0.06
    .SceneManagement
    -0.06
    NSDictionary
    -0.06
     lacking
    -0.06
    куль
    -0.06
     HOLDER
    -0.06
    POSITIVE LOGITS
    '''
    0.07
     rele
    0.07
     potential
    0.06
     sue
    0.06
     gst
    0.06
    tf
    0.06
     ©
    0.06
    (((
    0.06
     Interface
    0.06
    ฤด
    0.06
    Activations Density 0.145%

    No Known Activations