© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30124
    Prev
    Next
    INDEX
    Explanations

    Build configurations

    np_max-act · gemini-2.0-flash

    The neuron fires on the XML attribute values naming build targets or containers (e.g. the project/app “Name” and “Identifier” strings in an Xcode scheme file).

    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
    sweet
    -0.06
    ('%
    -0.06
     culture
    -0.06
    ownership
    -0.06
     VALID
    -0.06
     ik
    -0.06
    MaxY
    -0.06
     suốt
    -0.06
    )new
    -0.06
    ']],
    -0.06
    POSITIVE LOGITS
     Vuex
    0.07
     glide
    0.06
     FixedUpdate
    0.06
    _feed
    0.06
    udicots
    0.06
    失
    0.06
     Throughout
    0.06
     sklad
    0.06
     tầm
    0.06
    _templates
    0.06
    Activations Density 0.002%

    No Known Activations