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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 15-RESID-POST-AA
    6. 80948
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    punctuation marks and special characters used for document formatting and structural separation.

    oai_token-act-pair · claude-4-5-haikuTriggered by @bowenyi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kê
    -0.07
                                                 
    -0.07
    _four
    -0.07
     rawData
    -0.07
    >>(↵
    -0.06
     LGBTQ
    -0.06
                                                     
    -0.06
    tw
    -0.06
     earthquakes
    -0.06
     bo
    -0.06
    POSITIVE LOGITS
    =Integer
    0.07
    conomics
    0.06
    -too
    0.06
    LIC
    0.06
     goose
    0.06
    ственным
    0.06
    .test
    0.06
    ственный
    0.06
    _GUID
    0.06
    味
    0.06
    Activations Density 0.027%

    No Known Activations