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. 12935
    Prev
    Next
    INDEX
    Explanations

    Virginia

    np_max-act · gemini-2.0-flash

    specific names and identifiers associated with the state of Virginia.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on occurrences of the proper noun “Virginia,” marking references to the state 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
    _LOOK
    -0.07
     lcm
    -0.07
     nắm
    -0.07
     staffer
    -0.06
    .messaging
    -0.06
     rooted
    -0.06
     Rot
    -0.06
     pot
    -0.06
    .deepcopy
    -0.06
     Equals
    -0.06
    POSITIVE LOGITS
    Virginia
    0.12
     Virginia
    0.12
     Virgin
    0.10
    Virgin
    0.10
     virgin
    0.08
    yna
    0.08
    ira
    0.07
     vir
    0.07
     Olivia
    0.07
    inne
    0.07
    Activations Density 0.008%

    No Known Activations