Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 100978
    Prev
    Next
    INDEX
    Explanations

    Apache

    np_max-act · gemini-2.0-flash

    license-related information in software package descriptions.

    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
    suming
    -0.06
     sincerity
    -0.06
     �
    -0.06
     görün
    -0.06
     назнач
    -0.06
    	spec
    -0.06
    根
    -0.06
    ẹn
    -0.06
    会议
    -0.06
    遠
    -0.06
    POSITIVE LOGITS
     DO
    0.07
     violently
    0.07
     ως
    0.07
    ()==
    0.06
     gathers
    0.06
    olem
    0.06
    paces
    0.06
     fond
    0.06
    cola
    0.06
     Multimedia
    0.06
    Activations Density 0.004%

    No Known Activations