© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 68493
    Prev
    Next
    INDEX
    Explanations

    product descriptions

    np_max-act · gemini-2.0-flash

    The neuron fires on product feature/specification details (especially numeric measurements and technical specs).

    oai_token-act-pair · o4-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
     guideline
    -0.06
    rop
    -0.06
    -template
    -0.06
     plugs
    -0.05
     kernel
    -0.05
     bounds
    -0.05
    .app
    -0.05
    stringValue
    -0.05
    ideshow
    -0.05
     werde
    -0.05
    POSITIVE LOGITS
     Sabha
    0.06
    .databinding
    0.06
    Alignment
    0.06
    ERSION
    0.06
     KW
    0.06
     OnCollision
    0.06
     Throwable
    0.06
    ayız
    0.06
    
    0.06
    .MIN
    0.06
    Activations Density 0.103%

    No Known Activations