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. 91435
    Prev
    Next
    INDEX
    Explanations

    Tech products

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of specific branded hardware or product names (e.g., device names).

    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
     nejd
    -0.06
    ;",
    -0.06
     برنامج
    -0.06
     wirk
    -0.06
     bible
    -0.06
     وقد
    -0.06
    _am
    -0.06
    _known
    -0.06
     احتم
    -0.06
    онд
    -0.06
    POSITIVE LOGITS
     trim
    0.07
     Residents
    0.06
     Keeper
    0.06
     rowData
    0.06
    ,proto
    0.06
    _Controller
    0.06
     remnants
    0.06
    -ray
    0.06
    abstract
    0.06
    _figure
    0.06
    Activations Density 0.033%

    No Known Activations