© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 79597
    Prev
    Next
    INDEX
    Explanations

    documentation or code examples

    np_max-act · gemini-2.0-flash

    coding-related terms and syntax structures.

    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
    uestos
    -0.07
     logical
    -0.06
    -Star
    -0.06
    /her
    -0.06
     entrepreneur
    -0.06
    Ingredient
    -0.06
     cuis
    -0.06
    Located
    -0.06
    compare
    -0.06
    ніверсит
    -0.06
    POSITIVE LOGITS
     اخت
    0.07
     beraber
    0.07
    
    0.06
     لكل
    0.06
    μπο
    0.06
     bottom
    0.06
     actionTypes
    0.06
     최대
    0.06
     severed
    0.06
     Arbeit
    0.06
    Activations Density 0.030%

    No Known Activations