© 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. 51824
    Prev
    Next
    INDEX
    Explanations

    removing from start/end

    np_max-act · gemini-2.0-flash

    C# code structures that define methods for converting strings to various data types and handling whitespace.

    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
    �
    -0.06
    (`
    -0.06
    udas
    -0.06
     psychotic
    -0.06
    blocks
    -0.06
    ุทธ
    -0.06
    его
    -0.06
    alc
    -0.06
    ้องพ
    -0.06
    了解
    -0.06
    POSITIVE LOGITS
    平均
    0.07
     programa
    0.07
    removeAttr
    0.07
    '];?>↵
    0.07
     getIntent
    0.06
    ;",↵
    0.06
    ModelProperty
    0.06
    '],↵↵
    0.06
    foregroundColor
    0.06
    》（
    0.06
    Activations Density 0.028%

    No Known Activations