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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 12932
    Prev
    Next
    INDEX
    Explanations

    website

    np_max-act · gemini-2.0-flash

    The neuron flags the “Official website” link label (i.e. the site URL entry under External links).

    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
     دختر
    -0.08
    -stream
    -0.06
     svensk
    -0.06
    *'
    -0.06
    livě
    -0.06
     reflexivity
    -0.06
     hled
    -0.06
    .Art
    -0.06
     �
    -0.06
     toArray
    -0.06
    POSITIVE LOGITS
    updated
    0.08
    84
    0.06
     flexible
    0.06
     інститут
    0.06
    онов
    0.06
    елефон
    0.06
    .Entity
    0.06
     pang
    0.06
     temperature
    0.06
    컵
    0.06
    Activations Density 0.003%

    No Known Activations