© 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
    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. 73587
    Prev
    Next
    INDEX
    Explanations

    o

    np_max-act · gemini-2.0-flash

    The neuron is strongly activated by the substring “azo” (as in “azo dyes”), i.e. it detects occurrences of the “azo” chemical group in compound 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
    Trim
    -0.06
     Sı
    -0.06
    .TimeUnit
    -0.06
    λί
    -0.06
    723
    -0.06
    стве
    -0.06
    례
    -0.06
    گری
    -0.06
    InitialState
    -0.06
     Starr
    -0.06
    POSITIVE LOGITS
     glucose
    0.07
     dimensional
    0.06
    ократи
    0.06
     neph
    0.06
     cortisol
    0.06
     you
    0.06
    gency
    0.06
    üsseldorf
    0.06
     vowed
    0.06
    igure
    0.06
    Activations Density 0.001%

    No Known Activations