© 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. 92588
    Prev
    Next
    INDEX
    Explanations

    physical objects/equipment

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of “document file holder” (i.e. tokens referring to a document file‐holder device).

    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
    慌
    -0.07
    스테
    -0.07
    _students
    -0.07
    _INTR
    -0.07
    oses
    -0.06
    _listener
    -0.06
    (Vec
    -0.06
    _VLAN
    -0.06
    _list
    -0.06
     milli
    -0.06
    POSITIVE LOGITS
     compulsory
    0.08
    Related
    0.06
    .tipo
    0.06
     تخصص
    0.06
    講
    0.06
     Scott
    0.06
    arhus
    0.06
     سال
    0.06
    ASHINGTON
    0.06
    FFECT
    0.06
    Activations Density 0.155%

    No Known Activations