© 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. 77620
    Prev
    Next
    INDEX
    Explanations

    IBOutlet

    np_max-act · gemini-2.0-flash

    computer code and syntax elements.

    oai_token-act-pair · gpt-4o-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
     scorer
    -0.06
     strs
    -0.06
    cyan
    -0.06
     आज
    -0.06
    営
    -0.06
    Centre
    -0.06
    HASH
    -0.06
     paddingRight
    -0.06
    sorry
    -0.06
    .Writer
    -0.06
    POSITIVE LOGITS
    IBOutlet
    0.13
     IBOutlet
    0.12
     Colombian
    0.07
    押
    0.07
     Keyboard
    0.07
    ในท
    0.07
    esting
    0.07
    Touchable
    0.07
     قال
    0.07
     Clothing
    0.06
    Activations Density 0.000%

    No Known Activations