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. 73114
    Prev
    Next
    INDEX
    Explanations

    vaccinations and parents

    np_max-act · gemini-2.0-flash

    phrases and terms related to vaccination and public health advocacy.

    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
     incorporate
    -0.07
    logo
    -0.06
    .concat
    -0.06
    ('?
    -0.06
     cond
    -0.06
     stained
    -0.06
    words
    -0.06
     layout
    -0.06
     females
    -0.06
     Minor
    -0.06
    POSITIVE LOGITS
    delivr
    0.07
     ssize
    0.07
    เคร
    0.07
     만들
    0.07
    ]")]↵
    0.07
     flooding
    0.06
     darm
    0.06
     barang
    0.06
     datatable
    0.06
     Guzzle
    0.06
    Activations Density 0.010%

    No Known Activations