© 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. 540
    Prev
    Next
    INDEX
    Explanations

    spaceships

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of a spaceship (or related space-travel vehicle) and its actions (e.g., realizing, boarding, traveling).

    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
     Ко
    -0.07
    饭
    -0.07
     triệu
    -0.06
    .Tree
    -0.06
    -at
    -0.06
    	SET
    -0.06
    "Just
    -0.06
     Ang
    -0.06
    Subscription
    -0.06
    .Comparator
    -0.06
    POSITIVE LOGITS
     styled
    0.07
    .parseFloat
    0.07
    ัณฑ
    0.07
    承
    0.07
     raised
    0.07
     maior
    0.06
    ustil
    0.06
     serpent
    0.06
    nome
    0.06
     brazil
    0.06
    Activations Density 0.012%

    No Known Activations