© 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. 35503
    Prev
    Next
    INDEX
    Explanations

    with

    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
     controversy
    -0.07
     bred
    -0.07
    	bit
    -0.06
    之一
    -0.06
     modulation
    -0.06
    _Metadata
    -0.06
    ++;↵↵
    -0.06
    LOAD
    -0.06
     cultivated
    -0.06
    Archivo
    -0.06
    POSITIVE LOGITS
     теор
    0.07
     Cooler
    0.07
    ,(
    0.07
    .Te
    0.07
     una
    0.07
     člověk
    0.06
    078
    0.06
    >();
    0.06
     spoil
    0.06
    aybe
    0.06
    Activations Density 0.044%

    No Known Activations