© 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. 55579
    Prev
    Next
    INDEX
    Explanations

    international organizations

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on occurrences of the acronym “ALBA,” i.e. mentions of the Bolivarian Alliance for the Peoples of Our America.

    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
    _bounds
    -0.07
    š
    -0.07
    渐
    -0.07
    amped
    -0.06
     pep
    -0.06
    waters
    -0.06
    ีด
    -0.06
    CEPTION
    -0.06
    _Map
    -0.06
    psi
    -0.06
    POSITIVE LOGITS
    @author
    0.06
     Produk
    0.06
     Ave
    0.06
    porno
    0.06
     Recomm
    0.06
     tyranny
    0.06
    \Context
    0.06
     Memories
    0.06
     Include
    0.06
    "os
    0.06
    Activations Density 0.000%

    No Known Activations