© 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. 79598
    Prev
    Next
    INDEX
    Explanations

    recall or all

    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_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
     männer
    -0.08
     Ð
    -0.08
    /bar
    -0.07
    Hong
    -0.07
     Hong
    -0.07
     charg
    -0.07
    (button
    -0.07
     이미지
    -0.07
    .SubElement
    -0.07
    tgl
    -0.07
    POSITIVE LOGITS
     recall
    0.15
     Recall
    0.11
     recalling
    0.11
     recalled
    0.10
    recall
    0.10
     recalls
    0.10
     recount
    0.09
     rec
    0.09
     recap
    0.09
     recounts
    0.09
    Activations Density 0.012%

    No Known Activations