© 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. 55777
    Prev
    Next
    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash

    The neuron is detecting XML markup elements and Android manifest tag/attribute tokens (e.g. “<”, “android:…”, “activity”, “=” in manifests).

    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
    _df
    -0.07
    withdraw
    -0.07
     Swarm
    -0.06
     monthly
    -0.06
     powered
    -0.06
     شاخه
    -0.06
     rallied
    -0.06
     Swan
    -0.06
     melodies
    -0.06
     Boxes
    -0.06
    POSITIVE LOGITS
    oh
    0.07
    .ValidationError
    0.07
     Losing
    0.07
    �
    0.06
    ②
    0.06
    bservable
    0.06
    _IMPLEMENT
    0.06
    .Now
    0.06
    .Struct
    0.06
    ными
    0.06
    Activations Density 0.003%

    No Known Activations