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. 55269
    Prev
    Next
    INDEX
    Explanations

    dives

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “Maldives,” specifically picking up the “dives” subtoken in that country name.

    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
    _objs
    -0.07
     Victims
    -0.06
     firing
    -0.06
    .ProgressBar
    -0.06
     prosecuted
    -0.06
    filePath
    -0.06
     Validator
    -0.06
    Projects
    -0.06
     Ст
    -0.06
     Hamp
    -0.06
    POSITIVE LOGITS
    swana
    0.09
     Bahamas
    0.07
    utan
    0.07
    션
    0.07
     DDS
    0.06
    佛
    0.06
    (rhs
    0.06
    _TEAM
    0.06
     abundance
    0.06
     disclosure
    0.06
    Activations Density 0.005%

    No Known Activations