© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 22900
    Prev
    Next
    INDEX
    Explanations

    IS

    np_max-act · gemini-2.0-flash

    license-related details and permissions in text documents.

    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
     Hastings
    -0.06
    �
    -0.06
    ailer
    -0.06
    ("'
    -0.06
     bạc
    -0.06
     Pulitzer
    -0.06
     Cognitive
    -0.06
     weit
    -0.06
     jmen
    -0.06
    assembly
    -0.06
    POSITIVE LOGITS
     desperation
    0.07
     illustr
    0.07
    .mybatis
    0.07
     COM
    0.06
     благ
    0.06
    aurants
    0.06
     Com
    0.06
     workplace
    0.06
    느
    0.06
     misleading
    0.06
    Activations Density 0.002%

    No Known Activations