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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 105014
    Prev
    Next
    INDEX
    Explanations

    agreements and disagreements

    np_max-act · gemini-2.0-flash
    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
    indi
    -0.07
    LOCK
    -0.06
     dado
    -0.06
    SK
    -0.06
    rier
    -0.06
    order
    -0.06
    és
    -0.06
    ैर
    -0.06
    SIZE
    -0.06
     rá
    -0.05
    POSITIVE LOGITS
    >[]
    0.07
     ー
    0.07
     unpl
    0.07
     وقد
    0.07
    �
    0.06
    baş
    0.06
    処
    0.06
    =fopen
    0.06
     blij
    0.06
     hitters
    0.06
    Activations Density 0.060%

    No Known Activations