© 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. 100043
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    data structures related to JSON and object properties.

    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
    hte
    -0.08
     Someone
    -0.07
    =status
    -0.07
    -speed
    -0.07
    uste
    -0.06
     Connecting
    -0.06
    지역
    -0.06
    Someone
    -0.06
    Ai
    -0.06
    hc
    -0.06
    POSITIVE LOGITS
    €™
    0.07
     setContentView
    0.07
     вполне
    0.07
    なく
    0.06
     ENV
    0.06
    ocre
    0.06
     nepří
    0.06
    ــــ
    0.06
     presentViewController
    0.06
    ating
    0.06
    Activations Density 0.065%

    No Known Activations